The Flow has not summarised this story yet — read it at arXiv Computer Vision.
GaussVid introduces a 3D-aware video restoration framework that enhances sparse-view 3D Gaussian Splatting (3DGS) reconstructions. By creating a large-scale 3DGS video dataset and employing a camera-conditioned geometric prior anchored on the first and last frames, the method injects spatial structure into video generation, ensuring geometrically grounded restoration across viewpoints. Experiments demonstrate superior pixel- and structure-level fidelity (PSNR/SSIM) and improved multi-view consistency compared to other video-prior restoration methods, while maintaining competitive perceptual quality (LPIPS).
arXiv:2609.33253v2 Announce Type: replace Abstract: We present VGGT-Diff, a geometry-routed multi-view diffusion model for sparse-view novel view synthesis. Existing novel view synthesis (NVS) method...
ASV3D is a framework that adapts diffusion-based single-view 3D reconstruction to incorporate an additional image at test time. It offers a zero‑shot adaptation that improves reconstruction quality without retraining, and an optimized adaptation that uses contrastive learning to enhance visual fidelity and cross‑view consistency. The method is applied to two state‑of‑the‑art pipelines, showing consistent gains in accuracy and robustness on benchmark and real‑world datasets.
arXiv:2608.28895v1 Announce Type: new Abstract: We introduce ReconSplat, a feed-forward model for 3D scene reconstruction that aims to address the longstanding trade-off between plausible view genera...
PRISM is a feed‑forward single‑image 3D reconstruction framework that splits the task into a parameter‑free geometric warp and a learned residual correction, eliminating the need for iterative diffusion sampling. It uses a two‑stage training strategy—latent supervised distillation for geometric generalization and perceptual fine‑tuning for appearance quality—to generalize from synthetic data. Experiments on three benchmarks show PRISM matches diffusion‑based methods in quality while cutting inference time to just 36 seconds per scene.
The paper introduces ESC, a framework that improves 3D-consistent novel view synthesis from a single 2D image by jointly generating a target view and its depth map. By conditioning the diffusion model on the source image, source depth, and target camera rays, ESC forces the model to reason in 3D even under extreme viewpoint changes. A per‑pixel depth consistency constraint is added to enforce spatial fidelity, resulting in superior visual accuracy and spatial alignment compared to current state‑of‑the‑art methods.