Human Avatar Animation

Digital humans are fundamental to immersive interaction, yet creating a unified model for holistic modalities, including text, audio, motion, and visual content, remains an open challenge. In this paper, we present Archon, a fully pretrained, human-centric unified multimodal model for holistic avatar generation. Archon unifies seven modalities with modality-specific tokenizers, and a native autoregressive unified multimodal model pretrained on synchronized modalities and 72 diverse tasks to model holistic joint distributions. To address the token explosion challenge in high-fidelity talking videos, we introduce a memory-efficient semantic video reparameterization, achieving 4x token reduction while preserving fine-grained dynamics, coupled with a semantic-driven video diffusion decoder. We further propose a "Thinking in Modality" that decomposes ambiguous cross-modal tasks into stepwise thinking in an alternative chain of modality, progressively enhancing fidelity and controllability. Extensive experiments demonstrate that Archon achieves superior or comparable performance across diverse digital human generation tasks, validating the effectiveness of our unified framework. Project page: https://zju3dv.github.io/archon/.

Real-time synthesis of high-fidelity 3D character motion from audio is a pivotal component for next-generation interactive avatars and virtual assistants. However, most existing approaches are limited to offline processing of complete audio sequences or are constrained to specific domains, rarely handling both speech and music effectively. In this paper, we introduce a novel framework designed to generate continuous, coherent full-body motion from streaming speech and music with low latency. Central to our approach is a unified streaming architecture capable of synthesizing continuous motion from incremental audio inputs. We employ a robust training strategy that enforces strong audio dependency, allowing the model to seamlessly generalize across conversational speech and rhythmic music without requiring explicit domain labels or mode switching. Additionally, we explored Reinforcement Learning to refine the quality of online generation. Furthermore, we bridge reactive animation with intent-driven behavior via a tool-call interface that allows upstream Large Language Models to inject explicit semantic control. By combining this controllability with stream audio-driven synthesis, our framework serves as a plug-and-play solution for transforming voice agents into interactive humanoid avatars. Extensive experiments demonstrate that our method outperforms state-of-the-art realtime baselines in motion quality and synchronization while maintaining the flexibility required for live deployment. Our code, pre-trained models, and videos are available at https://robinwitch.github.io/EchoAvatar-Page.

Pose-driven full-body avatars built on neural rendering produce high-quality novel views of a captured subject. Yet loose clothing and other dynamic elements deform in ways pose alone cannot explain: the same pose can correspond to many different states, because their motion depends on history, inertia, and contact. Explicit simulation and layered-garment methods can model such dynamics, but they require either a dedicated garment template, which raw multi-view capture does not naturally provide, or a test-time physics simulator with non-trivial runtime cost. A parallel line of work learns data-driven clothing avatars that avoid explicit garment layers. These methods add an auxiliary latent for variation beyond pose; at inference, they fix it, regress it from pose, or retrieve it from training data, without explicitly modeling how the latent evolves with its own dynamics. Additionally, even in everyday motion with loose clothing, existing architectures often struggle to capture fine-grained detail, producing blurry renderings and temporal artifacts. We augment a pose-conditioned 3D Gaussian avatar with a transformer-based decoder and a dynamics residual latent that captures temporal appearance and geometry variation beyond the driving signals. At inference, a learned latent dynamics model evolves the residual latent from a short pose history and the previous latent state. The model decomposes each update into driving, restoring, and dissipative forces, producing temporally coherent, history-dependent rollouts with negligible added cost. Different initial conditions yield diverse yet plausible motion trajectories, and the force decomposition exposes controls such as stiffness. Across nine captured sequences of everyday motion with diverse loose garments, quantitative metrics and a perceptual user study show improved animation quality over recent data-driven baselines.

Existing Gaussian avatar methods typically parameterize geometry on a body-template surface, which entangles the avatar's representation space with the template's deformation space and limits the capture of layered, off-body, and non-rigid clothing geometry. We present PiG-Avatar, which addresses this limitation by using the parametric body model solely for kinematic transport, while representing the avatar as Gaussians anchored in a volumetric canonical space governed by a continuous neural field. This decouples representation from template topology, avoiding the geometric constraints of surface-based parameterizations. Kinematic coherence is maintained through 3D barycentric anchor transport, which guides motion without constraining geometry and allows anchors to deviate freely from the template surface, yielding dense, stable temporal surface correspondences by construction. To make this unconstrained formulation tractable, we introduce dual-level spatially coherent optimization, combining Sobolev-preconditioned neural-field updates with a novel KNN-based preconditioning of canonical anchor geometry. Together, these mechanisms induce an emergent self-organization of anchor density: anchors migrate toward regions of high curvature, appearance variation, and non-coherent motion without explicit heuristics. As a result, complex clothing geometry and layered surfaces emerge as natural, high-fidelity outputs. This single representation further supports hierarchical reconstruction across multiple levels of detail, with coarse-level supervision propagating to finer levels through the shared field and coupled anchor graph. On established benchmarks featuring subjects with complex clothing and challenging non-rigid motion, PiG-Avatar achieves state-of-the-art rendering quality, generalizes robustly to imperfect body model initialization, and renders in real time across all detail levels.

Avatar reconstruction has traditionally relied on per-subject optimization that requires hours of computation or on expensive preprocessing that limits scalability. We introduce FFAvatar, a generalizable feed-forward framework that reconstructs high-quality, animatable 3D Gaussian head avatars from few-shot unposed portrait images in seconds. FFAvatar fuses information from multiple source images into a unified canonical Gaussian representation through Multi-View Query-Former, which is animated via FLAME parameters predicted end-to-end directly from pixels, eliminating the overhead of offline FLAME extraction. We further propose a three-stage training curriculum that achieves both broad generalization and high-fidelity reconstruction: (i) scalable pretraining on extensive monocular video data with over 1M identities to learn strong generalizable priors; (ii) multi-view fine-tuning on a small but high-quality dataset of 360-degree captures to enhance geometric fidelity and extreme-view awareness; and (iii) optional personalization that adapts to specific identities for maximum fidelity within 500 optimization steps. Extensive experiments demonstrate that FFAvatar sets a new standard for identity preservation, geometric consistency, and animation fidelity. On the NeRSemble benchmark, it outperforms the state-of-the-art LAM by a substantial 5.5 PSNR gain. Furthermore, FFAvatar enables real-time deployment, reconstructing avatars in 2 seconds without personalization and 10 seconds with personalization, while supporting 49 FPS animation on a single NVIDIA A100 GPU.

The field of image-to-video generation has made remarkable progress. However, challenges such as human limb twisting and facial distortion persist, especially when generating long videos or modeling intensive motions. Existing human image animation works address these issues by incorporating human-specific semantic representations, e.g., dense poses or ID embeddings, as additional conditions. However, conditioning on these representations could decrease the generation flexibility. Moreover, their reliance on RGB pixel supervision also lacks emphasis on learning necessary 3D geometric relationships and temporal coherence. In contrast, we introduce a novel approach named SemanticREPA that leverages these semantic representations as supervision signals through representation alignment. Specifically, we begin by training a structure alignment module that aligns the structure representations obtained from video latents with video depth estimation features. We then fix the pretrained module, and utilize it to provide additional supervision on the structure representations of the diffusion models, achieving structure rectification to generate coherent and stable human structures. Simultaneously, we develop an ID alignment module to align the ID representations of the generated videos to face recognition features. We further propose to use the predicted structure representations to refine identity restoration in relevant regions. With structure and ID alignment, our method demonstrates superior quality on extended character motions and enhanced character consistency.

Human image animation has witnessed significant advancements, yet generating high-fidelity hand motions remains a persistent challenge due to their high degrees of freedom and motion complexity. While reinforcement learning from human feedback, particularly direct preference optimization, offers a potential solution, it necessitates the construction of strict preference pairs. However, curating such pairs for dynamic hand regions is prohibitively expensive and often impractical due to frame-wise inconsistencies. In this paper, we propose Implicit Preference Alignment (IPA), a data-efficient post-training framework that eliminates the need for paired preference data. Theoretically grounded in implicit reward maximization, IPA aligns the model by maximizing the likelihood of self-generated high-quality samples while penalizing deviations from the pretrained prior. Furthermore, we introduce a Hand-Aware Local Optimization mechanism to explicitly steer the alignment process toward hand regions. Experiments demonstrate that our method achieves effective preference optimization to enhance hand generation quality, while significantly lowering the barrier for constructing preference data. Codes are released at https://github.com/mdswyz/IPA

Existing talking avatar methods typically adopt an image-to-video pipeline conditioned on a static reference image within the same scene as the target generation. This restricted, single-view perspective lacks sufficient temporal and expression cues, limiting the ability to synthesize high-fidelity talking avatars in customized backgrounds. To this end, we introduce Talking Avatar generation from Video Reference (TAVR), a novel framework that shifts the paradigm by leveraging cross-scene video inputs. To effectively process these extended temporal contexts and bridge cross-scene domain gaps, TAVR integrates a token selection module alongside a comprehensive three-stage training scheme. Specifically, same-scene video pretraining establishes foundational appearance copying, which is subsequently expanded by cross-scene reference fine-tuning for robust cross-scene adaptation. Finally, task-specific reinforcement learning aligns the generated outputs with identity-based rewards to maximize identity similarity. To systematically evaluate cross-scene robustness, we construct a new benchmark comprising 158 carefully curated cross-scene video pairs. Extensive experiments show that TAVR benefits from flexible inference-time video referencing and consistently surpasses existing baselines both quantitatively and qualitatively. This work has been deployed to production. For more related research, please visit HeyGen Research and HeyGen Avatar-V.

We introduce MeshLAM, a feed-forward framework for one-shot animatable mesh head reconstruction that generates high-fidelity, animatable 3D head avatars from a single image. Unlike previous work that relies on time-consuming test-time optimization or extensive multi-view data, our method produces complete mesh representations with inherent animatability from a single image in a single forward pass. Our approach employs a dual shape and texture map architecture that simultaneously processes mesh vertices and texture map with extracted image features from a shared transformer backbone, allowing for coherent shape carving and appearance modeling. To prevent mesh collapse and ensure topological integrity during feed-forward deformation, we propose an iterative GRU-based decoding mechanism with progressive geometry deformation and texture refinement, coupled with a novel reprojection-based texture guidance mechanism that anchors appearance learning to the input image. Extensive experiments demonstrate that our method outperforms state-of-the-art approaches in reconstruction quality, animation capability, and computational efficiency. Project page at https://meshlam.github.io.

Building photorealistic, animatable full-body digital humans remains a longstanding challenge in computer graphics and vision. Recent advances in animatable avatar modeling have largely progressed along two directions: improving the fidelity of dynamic geometry and appearance, or reducing computational complexity to enable deployment on resource-constrained platforms, e.g., VR headsets. However, existing approaches fail to achieve both goals simultaneously: Ultra-high-fidelity avatars typically require substantial computation on server-class GPUs, whereas lightweight avatars often suffer from limited surface dynamics, reduced appearance details, and noticeable artifacts. To bridge this gap, we propose a novel animatable avatar representation, termed Wavelet-guided Multi-level Spatial Factorized Blendshapes, and a corresponding distillation pipeline that transfers motion-aware clothing dynamics and fine-grained appearance details from a pre-trained ultra-high-quality avatar model into a compact, efficient representation. By coupling multi-level wavelet spectral decomposition with low-rank structural factorization in texture space, our method achieves up to 2000X lower computational cost and a 10X smaller model size than the original high-quality teacher avatar model, while preserving visually plausible dynamics and appearance details closely resemble those of the teacher model. Extensive comparisons with state-of-the-art methods show that our approach significantly outperforms existing avatar approaches designed for mobile settings and achieves comparable or superior rendering quality to most approaches that can only run on servers. Importantly, our representation substantially improves the practicality of high-fidelity avatars for immersive applications, achieving over 180 FPS on a desktop PC and real-time native on-device performance at 24 FPS on a standalone Meta Quest 3.

We present EmbodiedHead, a speech-driven talking-head framework that equips LLMs with real-time visual avatars for conversation. A practical embodied avatar must achieve real-time generation, unified listening-speaking behavior, and high rendered visual quality simultaneously. Our framework couples the first Rectified-Flow Diffusion Transformer (DiT) for this task with a differentiable renderer, enabling diverse, high-fidelity generation in as few as four sampling steps. Prior listening-speaking methods rely on dual-stream audio, introducing an interlocutor look-ahead dependency incompatible with causal user--LLM interaction. We instead adopt a single-stream interface with explicit per-frame listening-speaking state conditioning and a Streaming Audio Scheduler, suppressing spurious mouth motion during listening while enabling seamless turn-taking. A two-stage training scheme of coefficient-space pretraining and joint image-domain refinement further closes the gap between motion-level supervision and rendered quality. Extensive experiments demonstrate state-of-the-art visual quality and motion fidelity in both speaking and listening scenarios.

Inverse kinematics (IK) is a core operation in animation, robotics, and biomechanics: given Cartesian constraints, recover joint rotations under a known kinematic tree. In many real-time human avatar pipelines, the available signal per frame is a sparse set of tracked 3D joint positions, whereas animation systems require joint orientations to drive skinning. Recovering full orientations from positions is underconstrained, most notably because twist about bone axes is ambiguous, and classical IK solvers typically rely on iterative optimization that can be slow and sensitive to noisy inputs. We introduce IK-GAT, a lightweight graph-attention network that reconstructs full-body joint orientations from 3D joint positions in a single forward pass. The model performs message passing over the skeletal parent-child graph to exploit kinematic structure during rotation inference. To simplify learning, IK-GAT predicts rotations in a bone-aligned world-frame representation anchored to rest-pose bone frames. This parameterization makes the twist axis explicit and is exactly invertible to standard parent-relative local rotations given the kinematic tree and rest pose. The network uses a continuous 6D rotation representation and is trained with a geodesic loss on SO(3) together with an optional forward-kinematics consistency regularizer. IK-GAT produces animation-ready local rotations that can directly drive a rigged avatar or be converted to pose parameters of SMPL-like body models for real-time and online applications. With 374K parameters and over 650 FPS on CPU, IK-GAT outperforms VPoser-based per-frame iterative optimization without warm-start at significantly lower cost, and is robust to initial pose and input noise

We propose a compositional method for constructing a complete 3D head avatar from a single image. Prior one-shot holistic approaches frequently fail to produce realistic hair dynamics during animation, largely due to inadequate decoupling of hair from the facial region, resulting in entangled geometry and unnatural deformations. Our method explicitly decouples hair from the face, modeling these components using distinct deformation paradigms while integrating them into a unified rendering pipeline. Furthermore, by leveraging image-to-3D lifting techniques, we preserve fine-grained textures from the input image to the greatest extent possible, effectively mitigating the common issue of high-frequency information loss in generalized models. Specifically, given a frontal portrait image, we first perform hair removal to obtain a bald image. Both the original image and the bald image are then lifted to dense, detail-rich 3D Gaussian Splatting (3DGS) representations. For the bald 3DGS, we rig it to a FLAME mesh via non-rigid registration with a prior model, enabling natural deformation that follows the mesh triangles during animation. For the hair component, we employ semantic label supervision combined with a boundary-aware reassignment strategy to extract a clean and isolated set of hair Gaussians. To control hair deformation, we introduce a cage structure that supports Position-Based Dynamics (PBD) simulation, allowing realistic and physically plausible transformations of the hair Gaussian primitives under head motion, gravity, and inertial effects. Striking qualitative results, including dynamic animations under diverse head motions, gravity effects, and expressions, showcase substantially more realistic hair behavior alongside faithfully preserved facial details, outperforming state-of-the-art one-shot methods in perceptual realism.

We present AHOY, a method for reconstructing complete, animatable 3D Gaussian avatars from in-the-wild monocular video despite heavy occlusion. Existing methods assume unoccluded input-a fully visible subject, often in a canonical pose-excluding the vast majority of real-world footage where people are routinely occluded by furniture, objects, or other people. Reconstructing from such footage poses fundamental challenges: large body regions may never be observed, and multi-view supervision per pose is unavailable. We address these challenges with four contributions: (i) a hallucination-as-supervision pipeline that uses identity-finetuned diffusion models to generate dense supervision for previously unobserved body regions; (ii) a two-stage canonical-to-pose-dependent architecture that bootstraps from sparse observations to full pose-dependent Gaussian maps; (iii) a map-pose/LBS-pose decoupling that absorbs multi-view inconsistencies from the generated data; (iv) a head/body split supervision strategy that preserves facial identity. We evaluate on YouTube videos and on multi-view capture data with significant occlusion and demonstrate state-of-the-art reconstruction quality. We also demonstrate that the resulting avatars are robust enough to be animated with novel poses and composited into 3DGS scenes captured using cell-phone video. Our project page is available at https://miraymen.github.io/ahoy/

Building one-shot 3D animatable head avatars is an important yet challenging problem. Existing methods generally collapse under large camera pose variations, compromising the realism of 3D avatars. In this work, we propose a new framework to tackle the novel setting of one-shot 3D full-head animatable avatar reconstruction in a single forward pass via inpainted UV-space Gaussian modeling, enabling 360$^\circ$ rendering views and real-time animation. To facilitate efficient animation control, we model 3D head avatars with Gaussian primitives embedded on the surface of a parametric face model within the UV space, and project the input image features to the UV space, resulting in incomplete local UV feature maps. To inpaint the missing regions, we obtain knowledge of full-head geometry and textures from rich 3D full-head priors within a pretrained 3D generative adversarial network (GAN) for global full-head feature extraction and multi-view supervision. Specifically, to enhance the fidelity of 3D reconstruction during inpainting, we take advantage of the symmetric nature of the UV space and human faces to fuse incomplete yet detailed local UV feature maps with the extracted global full-head textures, resulting in inpainted UV Gaussian attribute maps for avatar modeling. Extensive experiments demonstrate that our method is the first to achieve high-quality 3D full-head animatable avatar modeling, significantly improving side and back views while outperforming state-of-the-art animation approaches, thereby improving the realism of 3D animatable avatars.

Portrait animation has witnessed tremendous quality improvements thanks to recent advances in video diffusion models. However, these 2D methods often compromise 3D consistency and speed, limiting their applicability in real-world scenarios, such as digital twins or telepresence. In contrast, 3D-aware feedforward facial animation methods -- built upon 3D representations, such as neural radiance fields or Gaussian splatting -- ensure 3D consistency and achieve faster inference speed, but come with inferior expression details. In this paper, we address this portrait animation trilemma (speed, 3D consistency, and expressiveness) and propose a pipeline that instantly converts an in-the-wild single image into a 3D-consistent, fast yet expressive animatable representation via a feed-forward encoder. Unlike previous computationally intensive global fusion mechanisms (e.g., multiple attention layers) for fusing 3D structural and animation information, our design employs an efficient lightweight local fusion strategy to achieve high animation expressivity. Furthermore, our animation representation is decoupled from the face's 3D representation and learns motion implicitly from data, eliminating the dependency on pre-defined parametric models that often constrain animation capabilities. Our method runs at 107.31 FPS for animation and pose control, representing a 3-4 order of magnitude speedup versus the state of the art while achieving comparable animation quality, thus surpassing alternative designs that trade speed for quality or vice versa.

The generation of high-fidelity, animatable 3D human avatars remains a core challenge in computer graphics and vision, with applications in VR, telepresence, and entertainment. Existing approaches based on implicit representations like NeRFs suffer from slow rendering and dynamic inconsistencies, while 3D Gaussian Splatting (3DGS) methods are typically limited to static head generation, lacking dynamic control. We bridge this gap by introducing AGORA, a novel framework that extends 3DGS within a generative adversarial network to produce animatable avatars. Our key contribution is a lightweight, FLAME-conditioned deformation branch that predicts per-Gaussian residuals, enabling identity-preserving, fine-grained expression control while allowing real-time inference. Identity is further preserved through spatial shape conditioning of the identity branch, and expression fidelity is enforced via a dual-discriminator training scheme leveraging synthetic renderings of the parametric mesh. AGORA generates avatars that are not only visually realistic but also precisely controllable. Quantitatively, we outperform state-of-the-art NeRF-based methods on expression accuracy while rendering at 250 FPS on a single GPU and, notably, at $\sim$9 FPS under CPU-only inference -- to our knowledge the first demonstration of CPU-only animatable 3DGS avatar synthesis. This work represents a significant step toward practical, high-performance digital humans. Project website: https://ramazan793.github.io/AGORA/