Neural Rendering

Follow this topic Ask about this topic

Neural rendering studies how to represent scenes and light so computers can synthesize images from new viewpoints, times, or lighting conditions. Neural Radiance Fields (NeRFs) use implicit networks and differentiable volume rendering, while 3D Gaussian Splatting and other explicit primitives use rasterization or ray tracing; feed-forward and generative models aim to make reconstruction and rendering faster. Applications include dynamic scenes, avatars, relighting, neural materials, and sensor simulation, with quality often tested on benchmarks such as Mip-NeRF 360, LLFF, and DTU. A central challenge is balancing visual fidelity and geometric accuracy with speed, memory use, and reliable control of appearance under unseen views or lighting.

Latest papers

120 papers14 papers in the last four weeks, level with the four weeks before. 0.1% of all new papers.

RADIANT: Object-Centric Feed-Forward Global Illumination
Oct 23, 2026Sarah Zhang, Zhiyang Dou, Minghao Guo +2Neural Rendering Physically Based Rendering
MIT CSAIL
ART-MPG: Autoregressive R/T Manifold Path Guiding
Oct 21, 2026Zehao Zhao, Yanyang Yang, Xiaole Zhang +1Physically Based Rendering Importance Sampling
Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California · Computational Science and Engineering, Georgia Institute of Technology · Department of Electrical and Computer Engineering, Carnegie Mellon University
Directionally Factorized Illumination with Spherical Harmonic Rotation
Oct 17, 2026Yimeng Dou, Adam M. Saunders, Andre T. S. Hucke +5Neural Rendering Multi-View Image Synthesis
Department of Electrical and Computer Engineering, Vanderbilt University, Nashville, TN, USA · Department of Computer Science, Vanderbilt University, Nashville, TN, USA · Department of Biomedical Engineering, Vanderbilt University, Nashville, TN, USA +4
FlashReFocus: Interactive Image Refocusing in Seconds
Oct 16, 2026Ching-Heng Cheng, Chia-Ming Lee, Ming-Ching Chang +3Neural Rendering Diffusion Models for Image Restoration
National Cheng Kung University · State University of New York at Albany · National Yang Ming Chiao Tung University
RoboCloth: A Large-Scale Real Cloth Material Dataset for Neural Reflectance Reconstruction
Oct 15, 2026Zhen Li, Haoran Qin, Francesco Di Sario +2Neural Rendering Inverse Rendering
Simon Fraser University · Westlake University · University of Torino and Simon Fraser University +6
Spectral World Renderer: Unified 3D Hyperspectral Unmixing
Oct 14, 2026Chia-Ming Lee, Yu-Jou Hsiao, Ming-Ching Chang +3Hyperspectral Unmixing Spectral Unmixing
University at Albany, State University of New York · National Yang Ming Chiao Tung University · National Cheng Kung University
Gaussian Splatting with Reflections Guided by What is Seen
Oct 9, 2026Yiming Liang, Tianyu Xiao, Hiroshi IshikawaNeural Rendering Novel View Synthesis
Department of Computer Science and Communications Engineering, Waseda University, Japan
Volume Rendering with Metric--Phase Fields for Thin Structures and Sign-Ambiguous Geometry
Oct 9, 2026Junkai Deng, Jiayi Kong, Xuhui Chen +53D Reconstruction Multi-View 3D Reconstruction
College of Computing and Data Science, Nanyang Technological University, Singapore · Key Laboratory of System Software (Chinese Academy of Sciences), Institute of Software, Chinese Academy of Sciences, and the University of Chinese Academy of Sciences · Department of Computer Science, City University of Hong Kong, Hong Kong SAR, China +1
AgentGarten: Code Worlds for Evolving Agents
Oct 8, 2026Jiawei Chi, Shangchen Miao, Zhiyuan Shi +12Self-Evolving Agents Neural Rendering
MirroS Lab
AIMS: Anchor-Integrated Multi-View Synthesis for Scalable Novel View Rendering
Oct 6, 2026JooHyun Park, HanYoung Jang, HyeongYeop KangMulti-View Feature Fusion Neural Rendering
Korea University · NCSOFT
VCURF: Virtual Camera-based Uncertainty of Radiance Fields
Oct 2, 2026Liyan Chen, Nathaniel Burgdorfer, Philippos MordohaiUncertainty Quantification Neural Rendering
Stevens Institute of Technology
DAGS: Disentangled Appearance-and-Geometry Steering of a Frozen Image DiT for Temporally Stabilized Generative Rendering
Oct 1, 2026Karthik Mohan Kumar, Damian Andrysiak, Pedro Antonio Pena +2Controllable Image Generation Neural Rendering
Advanced Micro Devices, Inc. San Jose, USA · Advanced Micro Devices, Inc. Łódź, Poland · Advanced Micro Devices, Inc. Orlando, USA +1
NRF-GS: Neural Residual Fields for Expressive and Compact Gaussian Splatting
Sep 29, 2026Pratik Singh Bisht, Andreas Kolb3DGS Compression 3D Gaussian Splatting
Computer Graphics Group University of Siegen
SurgGMF: Fully Causal Gaussian Motion Forecasting for Anticipatory Surgical Scene Rendering
Sep 28, 2026Jingqian Sun, Yichao Tang3D Gaussian Splatting Neural Rendering
Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai, China · School of Mechanical Engineering, Tongji University, Shanghai, China · Shanghai Innovation Institute, Shanghai, China
ControlGS: Conditioning Neural Gaussians for Downstream-Processing-Aware XR Rendering
Sep 25, 2026Weikai Lin, Junjie Zhao, Carl Marshall +2Neural Rendering 3D Gaussian Splatting
University of Rochester, Rochester, USA · Reality Labs, Meta, Redmond, USA
Light Field Primitive for Novel View Synthesis
Sep 25, 2026Liang Chen, Jiahui Ning, Xun Jiang +4Novel View Synthesis Neural Rendering
Tongji University · Hong Kong Metropolitan University · City University of Hong Kong
DiffusionShadow: Diffusion-based Shadow Caching for Neural Volume Rendering
Sep 25, 2026Kai-Chen Tung, Qi Wu, David Bauer +3Neural Rendering Diffusion Model Caching
University of California, Davis, Davis, CA, United States · NVIDIA Spatial Intelligence Lab, Santa Clara, CA, United States · Argonne National Laboratory, Lemont, IL, United States
M-plicits: Neural Implicit Surfaces via Nested Multiscale Residuals
Sep 23, 2026Vinícius da Silva, Isabelle Melo, Matheus Bessa +8Implicit Neural Representations 3D Reconstruction
PUC-Rio · Universidade Federal de Santa Maria · Google DeepMind +2
BayesianGS-SLAM: Uncertainty-Aware Neural Rendering SLAM via Probabilistic Formulation
Sep 21, 2026Kyeongsu Kang, Seongbo Ha, Sibaek Lee +1Simultaneous Localization and Mapping 3DGS SLAM
Department of Intelligent Robotics, Sungkyunkwan University, Suwon, South Korea
IRIS: Implicit Rendering Matters for Pose-Free Novel View Synthesis
Sep 16, 2026Wenyu Li, Sidun Liu, Peng Qiao +2Novel View Synthesis Neural Rendering
National University of Defense Technology Changsha, China
Accelerating HKTex without Mesh Eigensystems: Local Unfolding and Randomized Thermal Features
Sep 12, 2026Zhewen He, Junyi Hu, Yi FangSpectral Methods Neural Rendering
New York University Abu Dhabi
Is Gaussian Splatting Becoming Neural Again? A Taxonomy and Controlled Study of Learned Parameterization
Sep 11, 2026YuanHang Wang, Xin Cao, Yi Zhang3D Gaussian Splatting 3D Reconstruction
University of Technology Sydney
LinearMask-GS: Stable-Mask Importance Pruning for Compact 3D Gaussian Splatting
Sep 9, 2026Donghun Ryu, Minhyeok Lee3DGS Compression 3D Gaussian Splatting
Department of Intelligent Semiconductor Engineering Chung-Ang University Seoul, Republic of Korea · School of Electrical and Electronics Engineering Chung-Ang University Seoul, Republic of Korea
From Explicit References to Scene Manifolds: Distributional Fidelity and Realism for Radiance Field Quality Assessment
Sep 7, 2026Saeed Mahmoudpour, Gi-Mun Um, Hyon-Gon Choo +13D Gaussian Splatting Neural Rendering
Vrije Universiteit Brussel, Department of Electronics and Informatics, Belgium · imec, Kapeldreef 75, B-3001 Leuven, Belgium · Electronics and Telecommunications Research Institute (ETRI), Republic of Korea
RenderFormer-V2: Neural Rendering with Heterogeneous Scene Primitives
Sep 4, 2026Chong Zeng, Yue Dong, Pieter Peers +2Neural Rendering 3D Scene Representation
Stanford University, USA · Microsoft Research, China · College of William & Mary, USA
FlashRender: Few-Step Generative Rendering via Camera-Controlled Video MeanFlow
Sep 3, 2026Byeongjun Park, Byung-Hoon Kim, Hyungjin ChungFlow Matching Camera-Controlled Video Generation
EverEx · Yonsei University · Korea University
P-CORE: Self-Supervised Surface Consistency for Point-Based Neural Editing
Sep 3, 2026Yanshu Zhang, Shichong Peng, Mehran Aghabozorgi +23D Shape Editing Self-Supervised Learning
Simon Fraser University, Canada · Alberta Machine Intelligence Institute (Amii), Canada · Canadian Institute for Advanced Research (CIFAR), Canada
MeshSuite: A Unified Benchmark for Triangle- and Mesh-Based Neural Rendering
Sep 1, 2026Kaixuan Zhang, Minxian Li, Mingwu Ren +1Neural Rendering
Nanjing University of Science and Technology · University of Surrey
ABCD: Alpha-Composited Block Coordinate Descent: Constant-VRAM Training for Large Radiance Fields
Aug 27, 2026Ka Heng Shiu, Kartic SubrNeural Rendering 3D Gaussian Splatting
The University of Edinburgh, Edinburgh, United Kingdom
Cross-Platform Benchmark of Neural 3D Reconstruction for Autonomous Laboratory Robots
Aug 26, 2026Yongho Kim, Mengjiao Han, Victor Mateevitsi +33D Reconstruction Neural Rendering
Argonne National Laboratory · University of Illinois Chicago · NAISE, Northwestern University

Oct 23, 2026J/K move · Enter open · S save

RADIANT: Object-Centric Feed-Forward Global Illumination

Sarah Zhang, Zhiyang Dou, Minghao Guo, Benjamin Tod Jones+1

MIT CSAIL

Neural Rendering Physically Based Rendering Object-Centric Representation Learning

Open paper AskPDF arXiv

Feed-forward neural renderers synthesize global illumination across novel 3D scenes without per-scene optimization or runtime ray tracing. Existing transformer-based renderers tokenize individual triangles, so self-attention scales quadratically with mesh resolution. Yet macroscopic radiative transport is governed by the underlying surface geometry and object arrangements rather than a particular mesh discretization; finer tessellation can thus inflate token counts without changing the underlying transport physics, motivating a discretization-agnostic and object-centric representation. We introduce RADIANT (RADiance-based Inter-Actor Neural Transformer), an object-centric architecture for feed-forward global illumination from point inputs. By representing each object with a compact budget of 32 surface-patch tokens, RADIANT decouples attention sequence length from polygon counts. In a single network, an inter-object scene transformer models 3D radiative exchange and a view decoder renders images at target camera poses. To capture light transport without materializing O(N^2) bias matrices, invariant form-factor attention embeds geometric distances and surface orientations directly into query-key dot products as SE(3)-invariant inner products weighted by learned area and material gains. For primary visibility without mesh connectivity, camera rays cross-attend scene tokens guided by depth-tested point splats in a shared spherical frame. Across a 1.03M-scene benchmark under matched model capacity, RADIANT reaches 25 dB tone-mapped PSNR in 5x fewer training steps than RenderFormer, and achieves 32.2 dB at 600k steps (+3.3 dB over RenderFormer and +7.6 dB over RenderFormer-V2). We further demonstrate the scalability of RADIANT, which completes a 512x512 forward pass of a 500-object scene in 0.83 s, with computational cost scaling with the number of objects rather than polygons.