scene-reconstruction

Tag

Cards List
#scene-reconstruction

TableVerse: A Large-scale Tabletop Dataset with Real-world Grounded Layouts for Generalizable Manipulation

Hugging Face Daily Papers · yesterday Cached

TableVerse introduces a fully automated Real2Sim pipeline that converts unstructured, in-the-wild images into high-fidelity, simulation-ready tabletop environments with accurate metrics and physical stability, along with a large-scale dataset (TableVerse-100K) for generalizable robotic manipulation.

0 favorites 0 likes
#scene-reconstruction

ATSplat: Compact Feed-forward 3D Gaussian Splatting with Adaptive Token Expansion

Hugging Face Daily Papers · 2d ago Cached

ATSplat introduces a feed-forward 3D Gaussian Splatting framework that uses adaptive 3D tokens to allocate primitives based on scene complexity, achieving state-of-the-art rendering quality while reducing the number of Gaussians by over 5.7 times compared to dense methods.

0 favorites 0 likes
#scene-reconstruction

WildCity: A Real-World City-Scale Testbed for Rendering, Simulation, and Spatial Intelligence

Hugging Face Daily Papers · 2026-07-07 Cached

WildCity introduces a large-scale multimodal dataset for city-scale urban navigation and spatial representation, collected by autonomous fleets. It provides 18 long trajectories and establishes baselines for reconstruction and closed-loop simulation to advance AI systems that can perceive and reason about city-scale environments.

0 favorites 0 likes
#scene-reconstruction

ZipSplat: Fewer Gaussians, Better Splats

Hugging Face Daily Papers · 2026-06-03

ZipSplat is a token-based feed-forward 3D Gaussian Splatting model that uses k-means clustering to decouple Gaussian placement from the pixel grid, achieving ~6x fewer Gaussians while setting new state-of-the-art results on DL3DV and RealEstate10K without requiring ground-truth poses or intrinsics.

0 favorites 0 likes
#scene-reconstruction

PropLLM: Propagation-Aware Scene Reconstruction for Network Fault Diagnosis

arXiv cs.AI · 2026-06-02 Cached

PropLLM integrates hop-by-hop scene reconstruction with LLMs for network fault diagnosis. It uses a dual-layer knowledge graph and a temporal causal propagation attention mechanism to trace back along propagation paths, improving accuracy and reducing hallucinations.

0 favorites 0 likes
#scene-reconstruction

RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video

Hugging Face Daily Papers · 2026-05-29 Cached

RayDer is a unified feed-forward transformer that consolidates camera estimation, scene reconstruction, and rendering for self-supervised novel view synthesis from real-world video, achieving clean power-law scaling and strong zero-shot performance.

0 favorites 0 likes
#scene-reconstruction

GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction

Hugging Face Daily Papers · 2026-05-22 Cached

GenRecon introduces a method for 3D scene reconstruction that integrates generative 3D priors with multi-view image conditioning, achieving high-fidelity, editable mesh reconstructions of indoor environments and outperforming existing methods by 16%.

0 favorites 0 likes
← Back to home

Submit Feedback