← Back to all news
arXiv Computer Vision By Yuchen Xia, Souvik Kundu, Mosharaf Chowdhury, Nishil Talati

Sphinx: Efficiently Serving Novel View Synthesis using Regression-Guided Selective Refinement

Read the original on arXiv Computer Vision →

Sphinx is a training‑free hybrid inference system for novel view synthesis that combines fast regression models with selective diffusion refinement. It first generates coarse views via regression, then applies diffusion only where needed to improve quality while reducing computation. An SLO‑aware scheduler dynamically allocates GPU resources, achieving up to 2.7× faster inference with less than 10% perceptual loss and up to 10× higher SLO attainment compared to FCFS scheduling.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

Hugging Face Trending Papers
Aug 3

StreamSplat: Streaming Feed-Forward 3D Gaussian Splatting

Feed-forward 3D Gaussian Splatting enables efficient novel-view synthesis without per-scene optimization, but most existing methods assume a fixed set of context views and process them jointly. This limits their applicability to online scenarios where calibrated views arrive sequentially and the scene must be updated causally.

benchmarks
More like this →
arXiv AI
Sep 28

Spackle: Completing Large View Single Image NVS with Adaptive Gaussians

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
diffusionbenchmarks
More like this →
arXiv Machine Learning
Sep 14

AnyView: Synthesizing Any Novel View in Dynamic Scenes

AnyView is a diffusion-based video generation framework designed for dynamic view synthesis, requiring minimal inductive biases or geometric assumptions. It trains a generalist spatiotemporal implicit representation using diverse data sources—monocular, multi-view static, and multi-view dynamic—to produce zero-shot novel videos from arbitrary camera locations and trajectories. The authors evaluate AnyView on standard benchmarks, introduce a new challenging benchmark called AnyViewBench for extreme dynamic view synthesis, and demonstrate that AnyView outperforms baselines in maintaining realistic, plausible, and spatiotemporally consistent videos across diverse real-world scenarios.

By Basile Van Hoorick, Dian Chen, Shun Iwase, Pavel Tokmakov, Muhammad Zubair Irshad, Igor Vasiljevic, Swati Gupta, Fangzhou Cheng, Sergey Zakharov, Vitor Campagnolo Guizilini
diffusionbenchmarks
More like this →