Pith. sign in

REVIEW 4 cited by

VEGS: View Extrapolation of Urban Scenes in 3D Gaussian Splatting using Learned Priors

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 2407.02945 v3 pith:HUWSB22Y submitted 2024-07-03 cs.CV

Sungwon Hwang , Min-Jung Kim , Taewoong Kang , Jayeon Kang , Jaegul Choo This is my paper · ORCID
classification cs.CV
keywords cameramethodsscenetrainingurbanviewknowledgemodel
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Neural rendering-based urban scene reconstruction methods commonly rely on images collected from driving vehicles with cameras facing and moving forward. Although these methods can successfully synthesize from views similar to training camera trajectory, directing the novel view outside the training camera distribution does not guarantee on-par performance. In this paper, we tackle the Extrapolated View Synthesis (EVS) problem by evaluating the reconstructions on views such as looking left, right or downwards with respect to training camera distributions. To improve rendering quality for EVS, we initialize our model by constructing dense LiDAR map, and propose to leverage prior scene knowledge such as surface normal estimator and large-scale diffusion model. Qualitative and quantitative comparisons demonstrate the effectiveness of our methods on EVS. To the best of our knowledge, we are the first to address the EVS problem in urban scene reconstruction. Link to our project page: https://vegs3d.github.io/.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

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

  1. G$^2$ARD-GS: Geometry-Guided Anchor-Regularized Gaussian Splatting Distillation

    cs.CV 2026-08 conditional novelty 6.0 of 10

    A progressive multi-round distillation scheme compresses LiDAR-assisted 3D Gaussian maps 5 to 30 times while preserving rendering quality and frozen-geometry reuse.

  2. JRN-Geo: A Joint Perception Network based on RGB and Normal images for Cross-view Geo-localization

    cs.CV 2025-09 conditional novelty 6.0 of 10

    Using monocular normal maps together with RGB images in a dual-branch fusion network improves cross-view geo-localization to state-of-the-art levels on University-1652 and SUES-200.

  3. sshELF: Single-Shot Hierarchical Extrapolation of Latent Features for 3D Reconstruction from Sparse-Views

    cs.CV 2025-02 conditional novelty 6.0 of 10

    sshELF reconstructs full 360-degree outdoor scenes from six sparse views in 0.18 seconds by generating intermediate virtual views before decoding 3D Gaussian primitives.

  4. ArbiViewGen: Controllable Arbitrary Viewpoint Camera Data Generation for Autonomous Driving via Stable Diffusion Models

    cs.CV 2025-08 conditional novelty 5.0 of 10

    ArbiViewGen generates arbitrary-viewpoint driving camera images by stitching the six input views into pseudo-target views and training a Stable Diffusion model to reconstruct the original views, enabling self-supervis...

Pith tools