Pith. sign in

REVIEW 9 cited by

Revisiting Depth Representations for Feed-Forward 3D Gaussian Splatting

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 2506.05327 v1 pith:HC2HN5YD submitted 2025-06-05 cs.CV

Duochao Shi , Weijie Wang , Donny Y. Chen , Zeyu Zhang , Jia-Wang Bian , Bohan Zhuang , Chunhua Shen This is my paper
classification cs.CV
keywords depthfeed-forwardaccurateboundariescloudsgaussiannovelobject
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Depth maps are widely used in feed-forward 3D Gaussian Splatting (3DGS) pipelines by unprojecting them into 3D point clouds for novel view synthesis. This approach offers advantages such as efficient training, the use of known camera poses, and accurate geometry estimation. However, depth discontinuities at object boundaries often lead to fragmented or sparse point clouds, degrading rendering quality -- a well-known limitation of depth-based representations. To tackle this issue, we introduce PM-Loss, a novel regularization loss based on a pointmap predicted by a pre-trained transformer. Although the pointmap itself may be less accurate than the depth map, it effectively enforces geometric smoothness, especially around object boundaries. With the improved depth map, our method significantly improves the feed-forward 3DGS across various architectures and scenes, delivering consistently better rendering results. Our project page: https://aim-uofa.github.io/PMLoss

Discussion (0). Sign in to comment.

Forward citations

Cited by 9 Pith papers

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

  1. AdaptSplat: Adapting Vision Foundation Models for Feed-Forward 3D Gaussian Splatting

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    AdaptSplat adds a Frequency-Preserving Adapter to vision foundation models to boost high-frequency fidelity and cross-domain performance in feed-forward 3D Gaussian Splatting.

  2. TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens

    cs.CV 2026-04 unverdicted novelty 7.0 of 10

    TokenGS uses learnable Gaussian tokens in an encoder-decoder architecture to regress 3D means directly, achieving SOTA feed-forward reconstruction on static and dynamic scenes with better robustness.

  3. TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    TriSplat predicts oriented triangle primitives from images in one forward pass to produce simulation-ready 3D meshes with competitive rendering quality.

  4. Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    The paper proposes a problem-driven taxonomy for feed-forward 3D scene modeling that groups methods by five core challenges: feature enhancement, geometry awareness, model efficiency, augmentation strategies, and temp...

  5. VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction

    cs.CV 2025-09 conditional novelty 6.0 of 10

    VolSplat predicts 3D Gaussians from a shared voxel grid instead of from image pixels, reporting large gains in sparse-view novel view synthesis on RealEstate10K, ScanNet, and ACID.

  6. AdaptSplat: Adapting Vision Foundation Models for Feed-Forward 3D Gaussian Splatting

    cs.CV 2026-05 unverdicted novelty 5.0 of 10

    AdaptSplat adds a lightweight Frequency-Preserving Adapter to vision foundation models that extracts direction-aware high-frequency priors and integrates them via positional encodings and residual modulation to improv...

  7. UniMesh: Unifying 3D Mesh Understanding and Generation

    cs.CV 2026-04 unverdicted novelty 5.0 of 10

    UniMesh unifies 3D mesh generation and understanding in one model via a Mesh Head interface, Chain of Mesh iterative editing, and an Actor-Evaluator self-reflection loop.

  8. DriveGen3D: Boosting Feed-Forward Driving Scene Generation with Efficient Video Diffusion

    cs.CV 2025-10 conditional novelty 4.0 of 10

    DriveGen3D makes long driving-video synthesis and 3D scene reconstruction practical by caching only the conditional diffusion branch, quantizing cross-view attention, and fusing temporal context into a feed-forward Ga...

  9. Visual Execution and Validation of Finite-State Machines and Pushdown Automata

    cs.FL 2025-08 unverdicted novelty 4.0 of 10

    Two new visualization tools for the FSM language step through all computations of nondeterministic finite-state machines and pushdown automata and let users check state properties during transitions.

Pith tools