The paper introduces TopoField, a deterministic decoder that bridges the gap between continuous semantic probability fields and discrete instance segmentation for functional parts in indoor point clouds. It aggregates multiple forward passes into a consensus field, decodes high‑confidence cores, constructs a pruned point graph, and applies a multi‑source graph‑geodesic partition to separate overlapping support regions. On the ECCV 2026 SceneFun3D Challenge, TopoField achieved second place with an AP of 28.286%, AP50 of 41.383%, and AP25 of 47.558%.
By Zhiwei Chen, Zhiheng Fu, Zixu Li, Mingyu Zhang, Jiale Huang, Yupeng Hu
The paper investigates how much semantic information is lost when frozen foundation models are combined for few‑shot 3D segmentation. By varying the number of retained semantic alternatives before fusion, the authors show that keeping the full distribution of class scores yields higher harmonic‑mean IoU than collapsing to a single class. Experiments on ScanNet200 and ScanNet++ confirm that full‑distribution fusion consistently outperforms top‑1 and other operators, and that most useful information is recovered by retaining a compact set of plausible alternatives.
By Silas Kwabla Gah, Ebenezer Owusu
Classical image correspondence is solved at the level of sparse keypoints or dense pixels, but the systems that consume these matches - object-level mapping, topological navigation, scene-graph maintenance - reason about whole objects. Recent work narrows this gap by matchng directly at the level of instance segments: a class-agnostic segmenter partitions each image, and per-segment descriptors are obtained by pooling features from large 3D foundation models over the masks.
arXiv:2608. 05774v1 Announce Type: cross Abstract: Joint-embedding predictive architectures learn by predicting latent representations of missing observations, yet many masked JEPAs are evaluated primarily through the encoders they produce.
By Zihan Zhou, Qifu Wen, Xi Zeng
VOIM (Voxel‑Grounded Online Instance Manager) is a training‑free system that builds open‑vocabulary 3D instance maps from RGB‑D or monocular RGB input by deferring label and instance decisions until sufficient soft evidence accumulates per voxel across views. Across four perception configurations on ScanNet++, VOIM outperforms the strongest online RGB‑D system, OVO‑SLAM, by 4.8–11.7 mIoU, and achieves 44.07 mIoU under a like‑for‑like protocol, winning all ten scenes. The method also runs unchanged on monocular RGB, matching baseline performance on Replica, and produces exportable occupancy grids that support free‑form instance queries.
By Sangmin Song, Sarath Kodagoda, Marc G. Carmichael, Karthick Thiyagarajan, Amal Gunatilake, Kelly Prentice, Jodi Martin
The paper introduces DIFTA-3D, a method that replaces the task‑specific visual branch in IIFNet3D with a frozen DINOv3 foundation model for RGB‑D 3D instance detection. It employs a depth‑consistent feature pipeline that projects points into calibrated RGB‑D frames, filters features with a metric depth‑residual check, caches accepted DINOv3 features, and aggregates them within proposal‑aligned RoI grids. Extensive experiments on ScanNetV2 show that the DINOv3 control achieves mAP scores of 76.15/60.93 at IoU thresholds 0.25/0.50, while the Conservative VAID recipe improves these to 76.59/62.16, indicating a modest gain from the proposed transfer recipe.
By Linman Wang, ZiFei Zhang, Chunran Zheng, Xiwang Dong, Jiarong Lin
arXiv:2608.28216v1 Announce Type: new
Abstract: Locating a specific object instance in a cluttered scene using a single reference image and a short description, and reporting when that instance is ab...
By Kishor Datta Gupta, Ahmed Rafi Hasan, Md. Mahfuzur Rahman, Md. Sadman Haque, Mohd Ariful Haque
The paper introduces Hardware‑aware Calibrated Clustered Attention (BC attention) to speed up the global attention layers of the Visual Geometry Grounded Transformer (VGGT) used for 3D scene reconstruction. By clustering queries within hardware‑friendly neighborhood blocks and adding hashing hyperplane calibration plus threshold‑based error compensation, BC attention reduces computation and memory traffic, enabling it to handle long sequences with practical latency gains on GPUs. Experiments show that calibrated BC attention accelerates global attention by 2.10–2.63× and the entire backbone by 1.77–2.35×, with only a 1% loss in accuracy, and achieves up to 2.87× latency improvement with less than 5% performance drop.
By Weitian Wang, Shubham Rai, Cecilia De La Parra, Akash Kumar
arXiv:2606.19828v2 Announce Type: replace
Abstract: 3D multimodal large language models (3D MLLMs) describe a 3D object as a whole but cannot address, name, or reason about its parts. Prior part-awar...
By Jintang Xue, Xinyu Wang, Yixing Wu, Jingwen Chen, C. -C. Jay Kuo
The paper introduces View‑Consistent Panoptic Quality (VC‑PQ), a new metric for evaluating multi‑view panoptic segmentation that treats each visible view equally and penalizes inconsistencies between predicted and ground‑truth visibility. VC‑PQ extends the traditional per‑scene PQ by decomposing the score into mask accuracy, view consistency, and matching threshold, and includes a parameter to recover area weighting for comparison. Experiments on ScanNet++ and ScanNetv2 show that VC‑PQ better reflects missed detections or ID changes across views than the conventional PQ^scene metric.
By Youngmin Lee, Byungha Ko, Guhnoo Yun, Dong Hwan Kim
The paper introduces TFA, a training‑free aggregation technique that calibrates frozen visual foundation models for visual place recognition. TFA uses cross‑codebook agreement, retrieval coverage, and spectral statistics to adjust residual assignment, spectral shaping, and global‑feature fusion without requiring place labels or task‑specific weights. Experiments with a DINOv2‑B backbone show significant Recall@1 gains over existing training‑free methods across multiple benchmarks, demonstrating that reliability‑guided aggregation can unlock additional retrieval performance from frozen representations.
By Xin Li, Zhimin Mao, Shang Wang, Siyuan Duan, Geng Zhang
arXiv:2608.30618v1 Announce Type: new
Abstract: Transformer-based decoders for 3D instance segmentation typically commit to a fixed number of queries and positional modeling calibrated on the trainin...
By Keno Moenck, Thorsten Sch\"uppstuhl