Related papers: VGG-T$^3$: Offline Feed-Forward 3D Reconstruction …
Sparse-view scene reconstruction often faces significant challenges due to the constraints imposed by limited observational data. These limitations result in incomplete information, leading to suboptimal reconstructions using existing…
Accurate quantification of forest coverage and combustible biomass (fuel load) is critical for wildfire risk assessment and ecosystem management. However, traditional methods relying on airborne LiDAR or field surveys are cost-prohibitive…
Streaming visual transformers like StreamVGGT achieve strong 3D perception but suffer from unbounded growth of key value (KV) memory, which limits scalability. We propose a training-free, inference-time token eviction policy that bounds…
Most existing 3D referring expression segmentation (3DRES) methods rely on dense, high-quality point clouds, while real-world agents such as robots and mobile phones operate with only a few sparse RGB views and strict latency constraints.…
We present Implicit-Scale 3D Reconstruction from Monocular Multi-Food Images, a benchmark dataset designed to advance geometry-based food portion estimation in realistic dining scenarios. Existing dietary assessment methods largely rely on…
Novel view synthesis (NVS) is increasingly relevant for edge robotics, where compact and incrementally updatable 3D scene models are needed for SLAM, navigation, and inspection under tight memory and latency budgets. Variational Bayesian…
3D Visual Grounding (3DVG) aims to locate objects in 3D scenes based on text prompts, which is essential for applications such as robotics. However, existing 3DVG methods encounter two main challenges: first, they struggle to handle the…
The rapid progress of large, pretrained models for both visual content generation and 3D reconstruction opens up new possibilities for text-to-3D generation. Intuitively, one could obtain a formidable 3D scene generator if one were able to…
Video Temporal Grounding (VTG), which aims to ground target clips from videos (such as consecutive intervals or disjoint shots) according to custom language queries (e.g., sentences or words), is key for video browsing on social media. Most…
Recent feed-forward networks have achieved remarkable progress in sparse-view 3D reconstruction by predicting dense point maps directly from RGB images. However, they often suffer from geometric inconsistencies and limited fine-grained…
Online free-viewpoint video (FVV) reconstruction is challenged by slow per-frame optimization, inconsistent motion estimation, and unsustainable storage demands. To address these challenges, we propose the Reconfigurable Continuum Gaussian…
Autonomous driving needs fast, scalable 4D reconstruction and re-simulation for training and evaluation, yet most methods for dynamic driving scenes still rely on per-scene optimization, known camera calibration, or short frame windows,…
Vision-centric retrieval for VQA requires retrieving images to supply missing visual cues and integrating them into the reasoning process. However, selecting the right images and integrating them effectively into the model's reasoning…
Efficient and scalable 3D surface reconstruction from range data remains a core challenge in computer graphics and vision, particularly in real-time and resource-constrained scenarios. Traditional volumetric methods based on…
Recently, linear complexity sequence modeling networks have achieved modeling capabilities similar to Vision Transformers on a variety of computer vision tasks, while using fewer FLOPs and less memory. However, their advantage in terms of…
Online 3D reconstruction from streaming inputs requires both long-term temporal consistency and efficient memory usage. Although causal variants of VGGT address this challenge through a key-value (KV) cache mechanism, the cache grows…
Large Vision Language Models (VLMs) effectively bridge the modality gap through extensive pretraining, acquiring sophisticated visual representations aligned with language. However, it remains underexplored whether these representations,…
In this paper, we present a novel, scalable approach for constructing open set, instance-level 3D scene representations, advancing open world understanding of 3D environments. Existing methods require pre-constructed 3D scenes and face…
Scene-level neural volumetric reconstruction from monocular videos remains challenging, especially under severe domain shifts. Although recent advances in vision foundation models (VFMs) provide transferable generalized priors learned from…
We present the first approach to build hierarchical task-driven 3D scene graphs of arbitrary indoor or outdoor environments using an uncalibrated monocular camera in real-time. We leverage geometric foundation models to estimate geometric…