PLSR: Progressive and Localized Super-Resolution of 3D Objects via Localized Latent Voxel Diffusion

Yuxin Liu; Minshan Xie; Jiawen Liang; Runsong Zhu; Chi-Wing Fu; Tien-Tsin Wong

cs.CVSep 6, 2026

PLSR: Progressive and Localized Super-Resolution of 3D Objects via Localized Latent Voxel Diffusion

Authors: Yuxin Liu, Minshan Xie, Jiawen Liang, Runsong Zhu, Chi-Wing Fu, Tien-Tsin Wong

Organizations: The Chinese University of Hong Kong, Hong Kong SAR, China · Guangdong University of Technology, China · City University of Hong Kong, Hong Kong SAR, China · Monash University, Australia

Abstract

High-resolution 3D asset generation is vital in various 3D applications. Existing state-of-the-art diffusion-based models remain constrained by fixed resolutions, limiting their ability to produce details. In this paper, we tackle the challenge of generating more detailed, higher-resolution 3D objects by introducing a 3D super-resolution (SR) framework built on existing 3D generative foundation models. To this end, we design PLSR, a progressive and localized super-resolution solution to achieve this goal effectively and memory efficiently. Technically, given a coarse geometry from a pretrained 3D generator, we decompose the global SR task into localized sub-tasks via an associative input decomposition scheme, adapt a flow-based 3D generator into a localized super-resolution model through low-cost finetuning, and unify them in an iterative patch-wise denoising pipeline for seamless high-resolution output. Experiments on challenging objects show that our approach is able to generate 3D details with new strong fine-detail fidelity while significantly reducing the computational cost, offering a new and practical solution for high-resolution 3D asset generation.

Figures & tables

Figure 1: We propose PLSR, a method that tackles the high-resolution mesh generation problem through P rogressive and L ocalized S uper- R esolution. Our method provides extra resolution increase over state-of-the-art 3D generation methods (e.g., TRELLIS.2). Zoom in to see the fine details.

Figure 2: Overview of our PLSR. Starting from a coarse mesh $O_{l}$ , we encode to obtain LR condition $Z_{l}$ , upsample to obtain the sparse voxel skeleton of HR latent, and initialize with Gaussian noise to form $Z_{h,T}$ . Rather than denoising $Z_{h}$ globally, we split $Z_{h}$ into fixed-size patches and crop $Z_{l}$ and image $I$ associatively to obtain a triplet, $(P_{h,t},P_{l},I_{p})$ . During iterative patch-wise denoising, our model iterates through the input tuples and predicts for each individual patch. The per-patch outputs are aggregated into a global prediction $v_{\rm pred}$ for denoising update. Once $Z_{h}$ is fully denoised, it can be decoded to an output mesh or be used as new LR condition $Z_{l}$ for the next SR round. Particularly, our localized SR process can be performed progressively to achieve higher resolution.

Figure 3: Architecture of our proposed localized SR model.

Panel of Figure 4 — Figure 4: Qualitative comparison on complex shape. Our method recovers fine details and avoids seams, while baselines show limited detail refinement ability. Zoom-in recommended.

Method	LPIPS ↓	FID ↓	HFR ↑	CD ↓	F1 ↑
TR.2(1536)	0.122	60.37	0.981	0.0247	0.059
TR.2(2560)	0.122	63.19	0.923	0.0225	0.036
UltraShape	0.167	72.03	0.876	1.3982	0.109
DetailGen3D	0.187	93.35	0.645	0.4600	0.083
Ours(2560)	0.109	55.89	1.088	0.0139	0.145

Table 1: Objective pseudo-GT evaluation. CD/HFR are scaled as indicated.

Figure 5: Qualitative ablation study. Given LR cues as anchors, our trained model suppresses most seams even without overlaps, and with overlapping applied, the seams are fully removed.

3D Asset Generation

3D asset generation creates and edits objects, characters, materials, and scenes from text, images, video, or geometric constraints.

See all 170 papers

FILIGREE3D: Scaling Sparse Latent Flow Matching for Ultra-High-Resolution Image-to-3D Generation
Sep 28, 2026Hongjie Li, Xinran Yang, Xiuchao Wu +2Flow Matching 3D ViTs
AlibabaGroup
NOFACE3D: NOise-scheduled Focused Anchoring and Controlled Enhancement for 3D Generation
Oct 9, 2026James Rose, Jingwen Liang, Wenchao Ma +23D Asset Generation
Roblox · The Pennsylvania State University
SR3R: Rethinking Super-Resolution 3D Reconstruction With Feed-Forward Gaussian Splatting
Feb 27, 2026Xiang Feng, Xiangbo Wang, Tieshi Zhong +73D Reconstruction 3D Gaussian Splatting
Hangzhou Dianzi University · ShanghaiTech University · Peking University +1

Sep 28, 2026J/K move · Enter open · S save

FILIGREE3D: Scaling Sparse Latent Flow Matching for Ultra-High-Resolution Image-to-3D Generation

Hongjie Li, Xinran Yang, Xiuchao Wu, Jiangjing Lyu+1

AlibabaGroup

Flow Matching 3D ViTs 3D Shape Generation Single-View 3D Reconstruction

Open paper AskPDF arXiv

Scaling image-to-3D generation to ultra-high resolutions requires controlling rapidly growing computational costs without sacrificing fine geometric detail. We present Filigree3D, a sparse latent flow-matching framework that generates 3D geometry from a single image at voxel resolutions up to

2048^3

, with straightforward extensibility to

4096^3

. To make training tractable, we introduce Structure-Aware Sparse Scaling, which combines spatial bounding with alternating local-global attention to constrain token growth while preserving both fine-scale details and long-range structural context. To enhance detail reconstruction, we curate training samples based on their high-resolution geometric gains and inject multi-scale image features into a sparse 3D DiT, effectively coupling structural semantics with fine-grained visual cues. Furthermore, a visibility-aware voxel regularization strategy improves robustness against sparse perturbations and facilitates the completion of unobserved geometry. Under our default configuration, Filigree3D maintains peak GPU memory consumption within practical limits for contemporary hardware, enabling the generation of highly intricate 3D geometry in approximately one minute. Extensive experiments demonstrate that our method yields substantial improvements in overall geometric fidelity and fine-detail preservation compared to existing baselines, validating practical, detail-preserving 3D generation at unprecedented resolutions.

Abstract

3D Asset Generation

Explore similar work

FILIGREE3D: Scaling Sparse Latent Flow Matching for Ultra-High-Resolution Image-to-3D Generation

NOFACE3D: NOise-scheduled Focused Anchoring and Controlled Enhancement for 3D Generation

SR3R: Rethinking Super-Resolution 3D Reconstruction With Feed-Forward Gaussian Splatting