Pith. sign in

REVIEW 12 cited by

Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2503.22236 v2 pith:BGVVDENO submitted 2025-03-28 cs.GR cs.CV

Chongjie Ye , Yushuang Wu , Ziteng Lu , Jiahao Chang , Xiaoyang Guo , Jiaqing Zhou , Hao Zhao , Xiaoguang Han This is my paper · ORCID
classification cs.GRcs.CV
keywords imagesgeometryhigh-fidelitygenerationhi3dgennormalbridgingdetails
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

With the growing demand for high-fidelity 3D models from 2D images, existing methods still face significant challenges in accurately reproducing fine-grained geometric details due to limitations in domain gaps and inherent ambiguities in RGB images. To address these issues, we propose Hi3DGen, a novel framework for generating high-fidelity 3D geometry from images via normal bridging. Hi3DGen consists of three key components: (1) an image-to-normal estimator that decouples the low-high frequency image pattern with noise injection and dual-stream training to achieve generalizable, stable, and sharp estimation; (2) a normal-to-geometry learning approach that uses normal-regularized latent diffusion learning to enhance 3D geometry generation fidelity; and (3) a 3D data synthesis pipeline that constructs a high-quality dataset to support training. Extensive experiments demonstrate the effectiveness and superiority of our framework in generating rich geometric details, outperforming state-of-the-art methods in terms of fidelity. Our work provides a new direction for high-fidelity 3D geometry generation from images by leveraging normal maps as an intermediate representation.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. RelaxFlow: Text-Driven Amodal 3D Generation

    cs.CV 2026-03 conditional novelty 6.5 of 10

    A training-free dual-branch flow method uses multi-prior consensus and attention-logit low-pass relaxation to text-steer occluded 3D geometry while preserving the observed image.

  2. ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation

    cs.CV 2026-07 unverdicted novelty 6.0 of 10

    ELSA3D introduces elastic semantic anchoring via sparse anchor tokens and a scale-aware octree tokenizer to unify 3D generation and captioning at reduced computational cost.

  3. TInR: Exploring Tool-Internalized Reasoning in Large Language Models

    cs.CL 2026-04 unverdicted novelty 6.0 of 10

    TInR-U internalizes tool knowledge into LLMs via bidirectional alignment, supervised fine-tuning, and reinforcement learning, outperforming standard tool-integrated reasoning in both in-domain and out-of-domain evaluations.

  4. Muses: Designing, Composing, Generating Nonexistent Fantasy 3D Creatures without Training

    cs.CV 2026-01 conditional novelty 6.0 of 10

    Muses creates new fantasy 3D animals by designing a combined skeleton, fusing voxel parts from separate 3D models along that skeleton, then restyling textures via image editing — with no training.

  5. One View, Many Worlds: Single-Image to 3D Object Meets Generative Domain Randomization for One-Shot 6D Pose Estimation

    cs.CV 2025-09 conditional novelty 6.0 of 10

    Given one RGB-D photo of an unseen object, an AI-generated 3D mesh, aligned jointly in metric scale and pose, yields state-of-the-art one-shot 6D pose estimation on YCBInEOAT, TOYL, and LM-O.

  6. PoseMaster: A Unified 3D Native Framework for Stylized Pose Generation

    cs.CV 2025-06 conditional novelty 6.0 of 10

    PoseMaster produces a 3D character mesh from one image and a target 3D skeleton, preserving identity and pose in a single unified model, and it outperforms two-stage 2D-to-3D baselines on the VRoid pose canonicalizati...

  7. Efficient Part-level 3D Object Generation via Dual Volume Packing

    cs.CV 2025-06 conditional novelty 6.0 of 10

    From a single image, a 3D latent diffusion model generates all parts of an object at once by packing the part structure into two non-overlapping volumes.

  8. PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers

    cs.CV 2025-06 conditional novelty 6.0 of 10

    PartCrafter generates several separable 3D part meshes at once from a single image by fine-tuning a pretrained 3D diffusion transformer with part identity tokens and local-global attention.

  9. ViewCraft3D: High-Fidelity and View-Consistent 3D Vector Graphics Synthesis

    cs.CV 2025-05 conditional novelty 6.0 of 10

    A two-stage method that fits 3D Bézier curves to a reconstructed mesh and refines them with a 3D diffusion prior, producing view-consistent 3D vector graphics from a single image in about 30 minutes.

  10. Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention

    cs.CV 2025-05 conditional novelty 6.0 of 10

    Direct3D-S2 uses a new Spatial Sparse Attention mechanism to train a sparse-volume diffusion transformer at 1024^3 resolution on 8 GPUs.

  11. Few-step Flow for 3D Generation via Marginal-Data Transport Distillation

    cs.CV 2025-09 conditional novelty 5.0 of 10

    MDT-dist distills a pretrained 3D flow model into a 1-2 step generator using velocity matching plus velocity distillation, cutting TRELLIS inference from 6.1s to 0.68s while approximately preserving generation quality.

  12. ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding

    cs.CV 2025-06 conditional novelty 5.0 of 10

    ShapeLLM-Omni unifies text, image, and 3D generation and understanding in one autoregressive LLM using discrete 3D tokens and a new 3D-Alpaca training dataset.

Pith tools