ProgResViT is an input‑adaptive Vision Transformer that processes images progressively across multiple rounds, starting with a low‑resolution image and a narrow subnetwork and refining the prediction with higher resolution and a wider subnetwork if needed. The method introduces Progress‑Conditioned Soft Gating (PSG) to share a single backbone across rounds while conditioning token fusion and layer outputs on the current round, block, and input resolution. Experiments on DeiT show improved accuracy‑compute trade‑offs compared to adaptive‑width, adaptive‑depth, and dynamic‑token baselines, and the design also benefits self‑supervised DINO representations and downstream semantic segmentation.
By Ali Hojjat, Janek Haberer, Olaf Landsiedel
SAM3Dual is a training‑free inference extension of pretrained SAM 3 that won third place in the MOSEv2 track of the 8th Large‑scale Video Object Segmentation Challenge. It separates temporal memory into short‑term and long‑term branches, fuses their responses deterministically, and modulates them with previous‑frame confidence, all while keeping SAM 3 parameters frozen. The approach achieved an official J&F score of 64.37, demonstrating competitive long‑term VOS performance without task‑specific training.
By JeongRae Kim, Chaehyun Kim, Changwon Lim
arXiv:2607. 13421v1 Announce Type: cross Abstract: Spatio-Temporal Video Grounding (STVG) aims to retrieve the visual trajectory of a specific object from a video stream as described by a natural language expression.
By Kai Chen, Ming Dai, Wenxuan Cheng, Wankou Yang
arXiv:2608. 03023v1 Announce Type: cross Abstract: Remote sensing semantic segmentation is hindered by costly pixel-level annotations, motivating training-free open-vocabulary methods.
By Changhao Zhao, Haoxiang Li, Yuke Li, Hai Liu, LingLin Zeng
arXiv:2608. 15062v1 Announce Type: cross Abstract: Scaling transformer language models creates an inherent tension between expressivity and memory efficiency.
By Amr Hegazy, Amr Alanwar, Mostafa Elhoushi
arXiv:2608.29126v1 Announce Type: new
Abstract: Referring single-object tracking enables language-grounded target initialization and subsequent tracking by jointly leveraging semantic cues and visual...
By Han Wang, Yuxuan Liu, Yuhan Sun, Jian Yang, Xiaotong Xu, Yixuan Lv, Zhuang Zhou, Shengyang Li
arXiv:2608.22064v1 Announce Type: new
Abstract: We present our solution for the MOSEv2 track of the 8th Large-scale Video Object Segmentation (LSVOS) Challenge at ECCV 2026. The challenge evaluates r...
By Mingqi Gao, Sijie Li, Jungong Han
arXiv:2604.19609v2 Announce Type: replace
Abstract: Transformers have become a common foundation across deep learning, yet 3D scene understanding still relies on specialized backbones with strong dom...
By Kadir Yilmaz, Adrian Kruse, Tristan H\"ofer, Daan de Geus, Bastian Leibe
arXiv:2604. 17376v2 Announce Type: replace-cross Abstract: In today's day and age, we face a challenge in detecting deepfake images because of the fast evolution of modern generative models and the poor generalization capability of existing methods.
By Kaliki V Srinanda, M Manvith Prabhu, Hemanth K Mogilipalem, Jayavarapu S Abhinai, Vaibhav Santhosh, Aryan Herur, Deepu Vijayasenan
LoopVAE introduces a recurrent depth architecture that reuses a scale‑ and loop‑conditioned core across different spatial scales while keeping resolution‑changing transitions separate. The four‑block core applies 28 block operations per encoder or decoder, enabling a 29M‑parameter convolutional model to achieve 0.28 rFID and 32.54 dB PSNR on ImageNet‑256 with roughly 65% fewer parameters than comparable VAEs. Experiments with both convolutional and Transformer operators, as well as ablations on parameter sharing, demonstrate competitive image quality metrics and reveal how targeted loop interventions and truncation affect reconstruction quality and computational trade‑offs.
By Zhiying Lu
CameraEditor is a new framework that transforms camera-controlled image editing into a temporal sequence prediction problem. By using video diffusion models, it incorporates a geometric perception module and dynamic reference routing to create precise visual references through dynamic panorama cropping. The method also inserts intermediate transition frames to handle large perspective shifts, maintaining content identity and spatial coherence, and is evaluated on a dataset of 5,760 instances with a benchmark of 462 test cases, achieving state‑of‑the‑art performance.
By Xin Shen, Chengyou Jia, Keshuo Xing, Zifeng Zhu, Changliang Xia, Bowen Ping, Zhuohang Dang, Hangwei Qian, Minnan Luo
Streaming 3D reconstruction relies on a compact recurrent scene state to process long image streams in linear time and bounded memory. However, repeated updates can gradually corrupt this state, causing reliable historical information to be overwritten by noisy or ambiguous observations.