Spackle is a lightweight residual learning framework designed to improve large-view single-image novel view synthesis (NVS) by mitigating capacity competition in hybrid decoupled systems that combine 3D Gaussian Splatting (3DGS) and diffusion models. It operates in three stages: predicting base 3DGS attributes, automatically identifying poorly reconstructed regions, and learning a residual 3DGS focused on those areas. During inference, Spackle merges the baseline and augmented Gaussians to produce high-fidelity novel views, achieving state‑of‑the‑art performance on large-view-deviation cases.
By Xuanzhi Liu, Yuhe Zhou, Xinyi Wu, Zhenyao Wu, Jinghao Chen, Ruize Han, Song Wang
V-Co investigates visual co-denoising for pixel-space diffusion models, using a unified JiT-based framework to isolate key design choices. The study identifies two essential components: a dual-stream architecture with flexible cross-stream interaction and a perceptual-drifting hybrid loss combined with RMS-based feature rescaling for stronger semantic supervision. Experiments on ImageNet-256 demonstrate that V-Co surpasses baseline pixel-space diffusion and strong prior pixel-diffusion methods at comparable model sizes while requiring fewer training epochs.
By Han Lin, Xichen Pan, Zun Wang, Yue Zhang, Chu Wang, Jaemin Cho, Mohit Bansal
arXiv:2609.39709v1 Announce Type: new
Abstract: Recent diffusion-based pipelines have achieved promising progress in image-to-3D synthesis. However, generating high-fidelity details remains challengi...
By Junyu Li, Qiuyu Chen, Pengcheng Wang, Shiqi Yang, Alexandra Gomez-Villa, Joost van de Weijer, Ruilin Li, Kai Wang
Pixel‑Space Diffusion via Observation Operators introduces a new framework for pixel‑space diffusion models that addresses a scale‑time mismatch in existing methods. By replacing fixed full‑image supervision with a time‑indexed observation trajectory that progresses from coarse structures to the full image, the model aligns supervision with the natural recovery order of image details. The approach employs Gaussian‑Lanczos operators and a GL‑CoDA decoder to refine features progressively, resulting in faster convergence and higher generation quality, achieving an FID of 1.52 on ImageNet‑256.
By Shaojie Guo, Lichen Ma, Haoyang Tong, Yu He, Zipeng Guo, Xiaoan Liu, Feng Yan, Yu Guo, Fei Wang, Junshi Huang, Yan Wang
The paper introduces a decoder that generates images whose features closely match a user-specified feature, enabling detailed analysis of a vision-related deep neural network’s feature space. Implemented as a guided diffusion model, it steers a pre-trained diffusion model to minimize the Euclidean distance between the feature of a clean image and the target feature at each generation step. The method is training‑free, works on a single COTS GPU, and has been validated on CLIP’s image encoder and ResNet‑50, showing high feature‑matching accuracy and practical feasibility.
By Kimiaki Shirahama, Kaduki Yamashita, Miki Yanobu, Miho Ohsaki
arXiv:2605.12957v2 Announce Type: replace
Abstract: Recent developments in generative models and large-scale datasets have substantially advanced 3D world generation, facilitating a broad range of do...
By Hanxin Zhu, Cong Wang, Peiyan Tu, Jiayi Luo, Tianyu He, Xin Jin, Zhibo Chen
Recent advances in diffusion models have shown impressive performance in controllable image generation and dense prediction tasks. However, existing approaches typically treat diffusion-based controllable generation and dense prediction as separate tasks, overlooking the potential benefits of jointly modeling the heterogeneous distributions.
Diffusion models have achieved remarkable success in image and video generation, yet the high computational cost of iterative sampling remains a critical bottleneck for practical deployment. Feature c...
GS-PI introduces an optimization‑decoupled framework that transforms Gaussian Splatting (GS) assets into physically based rendering (PBR) compatible Gaussian assets. By treating PBR material generation as a geometry‑conditioned diffusion process on 3D point clouds, it achieves multi‑view consistency and avoids the pixel‑correspondence problems of 2D diffusion. The method employs a multi‑scale cross‑view conditioning mechanism—combining global semantic priors, photometric cues, and spatial view‑direction signals—to prevent specular highlights from baking into intrinsic colors, and then distills the predicted attributes back into a fully relightable PBR‑GS asset without requiring proxy meshes.
By Jieting Xu, Rengan Xie, Zijian Huang, Zehui Jin, Rui Wang, Yuchi Huo
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.
Unified image restoration (UIR) aims to recover high-quality (HQ) content from low-quality (LQ) images with different degradations using a single model. Most recent methods adapt large pretrained text-to-image (T2I) latent diffusion models for their strong capacity and generative priors.
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