We introduce ReconSplat, a feed-forward model for 3D scene reconstruction that aims to address the longstanding trade-off between plausible view generation for unobserved regions and geometric consistency, providing both geometrically aligned novel views and sharp depth estimates. Our approach builds on 3D Gaussian splatting (3DGS) as an intermediate differentiable scene representation and integrates it with a multi-view latent diffusion model (MV-LDM) trained to act simultaneously as a refiner and an inpainter for appearance and scene geometry. We enforce geometric consistency by guiding the diffusion process with variational 3D latent features for appearance and geometry, encoded by the feed-forward 3DGS representation and rasterized to 2D latent space. ReconSplat produces both photorealistic novel views and accurate depth maps on real-world benchmarks, RealEstate10K and DL3DV-10K, outperforming existing methods in challenging extrapolation setups. Notably, ReconSplat allows the extrapolation of unseen and challenging viewpoints jointly with coherent and precise scene geometry.
SpatialCrafter is presented, a novel two-stage framework that addresses explorable image-to-scene generation issues by introducing a global 3D proxy for high-fidelity image-to-scene generation and appearance refinement and introduces Parallel Geometry Injection and Proxy-Aware Corruption training strategies.
Chuan Fang, Lingteng Qiu, Yixun Liang et al.· 3 citations
4D scene reconstruction aims to recover the evolving geometry, appearance, and motion of dynamic environments from visual observations. Despite substantial progress in neural scene representations, reconstructing dynamic scenes remains challenging due to non-rigid motion, occlusions, temporal inconsistencies, and the t...
Zi-Ren Gong, Guo Chen, Yong-Jian Li et al.· 1 citation
RoGe is an end-to-end unified reconstruction and generation framework that removes this explicit bridge between reconstruction and generation, and outperforms reconstruction-based, generation-based, and hybrid baselines in terms of image-level quality and video-level temporal and geometric consistency.
Xiao-Lei Lang, Ze Kang, Ze-Hao Huang et al.· 0 citations
CasDeblurGS is proposed, a cascaded framework that progressively recovers reliable cross-view information from local 2D correspondences to global 3D guidance that enables a more coherent 3D representation and higher-quality novel-view synthesis.
AnyGS2Mesh is presented, the first feed-forward framework for directly reconstructing 3D meshes from 3D Gaussian Splatting representations with support for arbitrary input image resolutions, and demonstrates the potential of combining Gaussian representations and feed-forward Transformer architectures for scalable 3D g...
Yuxuan Song, Fan Gao, Yi-Bo Zhao et al.· 0 citations
RIGOR is a large-scale reconstruction pipeline for gravity-aligned omnidirectional videos that retains a frozen feed-forward perspective backbone and exploits each panorama as a four-view virtual rig and improves both trajectory accuracy and reconstructed geometry over a feed-forward baseline on challenging constructio...
Ting-Jun Huang, Dmitry Rudshin, Mathieu Meyer et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
