NeurIPS 2026 Papers

Monocular online 3D instance segmentation enables embodied agents to build object-level 3D understanding while continuously exploring their environments. Unlike RGB-D settings, monocular RGB streams lack direct depth and camera pose information, making geometry reconstruction necessary for 3D segmentation. Recent reconstruction foundation models (RFMs) have made this task more feasible by recovering 3D geometry and cross-view cues from monocular images. However, reconstructed geometry remains noisy and incomplete, and streaming observations provide only partial views of object instances, making local observations insufficient for stable instance representations and temporally consistent segmentation. We propose MonoChunk3D, an online 3D instance segmentation framework that incrementally reconstructs, aligns, and segments incoming monocular RGB chunks. Rather than treating reconstructed geometry merely as input, the framework adaptively integrates complementary RFM-derived cross-view priors with 3D geometric features to initialize current-chunk instance queries. To overcome the limitations of local observations, we maintain compact persistent instance states composed of explicit prototypes, implicit query embeddings, and spatial bounds to preserve long-term instance context. These states are propagated as history-aware queries and jointly decoded with current-chunk queries, allowing the preserved instance context to directly guide current-chunk segmentation. The resulting predictions are associated with historical instances to update the persistent states, enabling temporally consistent segmentation over streaming observations. Experiments on ScanNet200, ScanNetV2, and SceneNN show that MonoChunk3D achieves consistent improvements over existing methods in the monocular online setting.

Spherical Transformers have emerged as a promising framework for panoramic semantic segmentation (PASS) by operating directly on spherical geometry and alleviating projection-induced distortions. However, existing architectures rely on assumptions of canonical spherical structure and stable viewpoints, which are frequently violated in real-world $360^\circ$ imagery due to unconstrained camera motion, introducing significant contextual and geometric ambiguity. Consequently, they lack adaptive mechanisms to model such ambiguity, limiting robustness to unseen spherical transformations. In contrast, biological perception is inherently ambiguity-aware: rather than estimating uncertainty probabilistically, it adapts to fluctuations in cue reliability caused by geometric and contextual variations, enabling stable interpretation under complex visual transformations. Motivated by these observations, we first present a systematic analysis of existing PASS architectures under various unseen spherical transformations. Following this, we introduce AdapToPASS, a novel, bio-inspired Spherical Transformer that adaptively models contextual and geometric ambiguities for robust panoramic semantic segmentation. At the core of AdapToPASS are the Adaptive Spherical Attention (AdaSpA) blocks that dynamically modulate attention according to local contextual ambiguity, mimicking the adaptive, context-driven perception of biological vision. To address geometric ambiguities, AdapToPASS employs Bifocal Spherical Representation that reconciles the trade-off between field of view and spatial resolution; along with boundary supervision to emulate the boundary-sensitive nature of biological vision. We evaluate AdapToPASS in both indoor and outdoor semantic segmentation, where it consistently outperforms prior state-of-the-art methods. We further validate AdapToPASS under unseen spherical transformations, where it demonstrates strong robustness and surpasses the next-best method by +13.38% relative improvement in mIoU on Stanford2D3D and +18.77% on WildPASS. Additionally, we introduce a lightweight variant, AdapToPASS-Tiny, with fewer than 2M parameters, which surpasses compact baselines while retaining robustness to spherical transformations.