arXiv AI

Reflection-aware Generative Novel View Synthesis

The paper introduces Ref-GeNVS, a training‑free, reflection‑aware approach for generative novel view synthesis in mirror scenes. It treats a mirror image as two complementary views, estimates the mirror plane and reflected camera poses, and uses a two‑stage generation process with Mirror‑gated attention and Reflection injection to produce reflection‑consistent novel views. The method leverages a multi‑view diffusion backbone without finetuning, outperforming recent generative NVS methods on synthetic and real mirror scenes.

arXiv Computer Vision
Sep 4

Fill My Mirror: Geometry-Constrained Mirror Inpainting

The paper introduces a method for mirror inpainting that leverages scene geometry to generate realistic reflections. By estimating the geometry of the fixed scene, the approach projects visible content into the mirror region, reducing the need for hallucination. A two‑mask diffusion strategy then refines the mirror area, balancing geometric constraints with learned priors, and the method operates without training on complex real‑world scenes.

By Ofek Basson, Shimon Vainer, Yacov Hel-Or, Ohad Fried
arXiv Computer Vision
Sep 3

RoGe: Novel View Synthesis via End-to-End Implicit Reconstruction and Generation

RoGe is a new end‑to‑end framework for novel view synthesis that jointly learns an implicit 3D scene representation and a video diffusion model. It eliminates the need for explicit 3D intermediates by querying the implicit scene with camera rays to produce geometric features that condition the diffusion model. Experiments on DL3DV show that RoGe surpasses reconstruction‑based, generation‑based, and hybrid baselines in image quality and temporal consistency, and ablations confirm the benefits of ray‑queried features and joint training.

By Xiaolei Lang, Ze Kang, Zehao Huang, Naiyan Wang
arXiv Computer Vision
Sep 4

Stabilizing Camera-Controlled Novel View Synthesis at Inference Time

The paper introduces CamTrol++, a training‑free method that stabilizes camera‑controlled novel view synthesis from a single image by decomposing large camera motions into small autoregressive steps, thereby limiting per‑step distortion and error accumulation. It also incorporates geometry‑constrained spatial attention, low‑frequency appearance anchoring, and a registration‑free warping pipeline to further enhance stability. Experiments on RealEstate10K and MegaScene demonstrate improved temporal and geometric consistency, better downstream 3D reconstruction quality, and higher generation efficiency, even for long 56‑frame sequences and under depth corruption.

By Prajwal Singh, Arjun Badola, Seema Kumari, Hajime Nagahara, Shanmuganathan Raman
arXiv AI
4d ago

RelightFormer: Feed-forward Generative Transformer for Multiview Object Relighting

RelightFormer is a feed‑forward generative Transformer that performs single‑ and multi‑view image relighting without explicit intrinsic property estimation. It incorporates a latent illumination module that injects target environment maps into spatial features via cross‑attention, and uses permutation‑invariant positional encodings to process unordered multi‑view inputs symmetrically. Trained on the large Laval Objaverse Dataset, the model achieves state‑of‑the‑art visual and photorealistic relighting quality, and demonstrates strong zero‑shot generalization across various relighting tasks.

By Hejun Wang, Jinxi Li, Junwei Jiang, Shiwei Mao, Hu Cheng, Shouwang Huang, Bo Yang
Hugging Face Trending Papers
Jun 24

PRISM: Feed-Forward Single-Image 3D Reconstruction via Geometric Warp-Residual Modeling

Reconstructing 3D scenes from a single image is a fundamental challenge in computer vision, with broad applications in virtual reality, robotics, and content creation. Recent methods achieve outstanding performance by leveraging camera-controlled video diffusion models, but rely on iterative diffusion sampling, which greatly limits their practical deployment.

arXiv Computer Vision
Aug 28

SpatialCrafter: Single Image World Modeling with Generative 3D Proxies

SpatialCrafter introduces a two‑stage framework for single‑image world modeling that first generates a global 3D proxy using a Point‑anchored Sparse Structure Flow module, then refines appearance with a Generative Deferred Refiner built on a video diffusion model. The method incorporates Parallel Geometry Injection and Proxy‑Aware Corruption training to integrate the proxy without disrupting the pretrained generative manifold, and it is evaluated on a newly constructed dataset of 115K scenes. Experiments demonstrate that SpatialCrafter outperforms existing approaches, reducing long‑term drift and maintaining consistency under rapid camera motion and extreme viewpoints.

By Chuan Fang, Lingteng Qiu, Yixun Liang, Rui Chen, Kunming Luo, Zhaohua Zheng, Tongyuan Bai, Feipeng Tian, Zilong Dong, Zihan Zhou, Ping Tan