Related papers: V-DPM: 4D Video Reconstruction with Dynamic Point …
In this paper, we are interested in self-supervised learning the motion cues in videos using dynamic motion filters for a better motion representation to finally boost human action recognition in particular. Thus far, the vision community…
Visual place recognition (VPR) aims to determine the general geographical location of a query image by retrieving visually similar images from a large geo-tagged database. To obtain a global representation for each place image, most…
Recently, 3D vision-based diffusion policies have shown strong capability in learning complex robotic manipulation skills. However, a common architectural mismatch exists in these models: a tiny yet efficient point-cloud encoder is often…
Panoptic segmentation of 3D scenes, involving the segmentation and classification of object instances in a dense 3D reconstruction of a scene, is a challenging problem, especially when relying solely on unposed 2D images. Existing…
Realistic simulation is critical for applications ranging from robotics to animation. Traditional analytic simulators sometimes struggle to capture sufficiently realistic simulation which can lead to problems including the well known…
Dynamic scene reconstruction from casual videos has seen recent remarkable progress. Numerous approaches have attempted to overcome the ill-posedness of the task by distilling priors from 2D foundational models and by imposing hand-crafted…
Video stabilization aims to mitigate camera shake but faces a fundamental trade-off between geometric robustness and full-frame consistency. While 2D methods suffer from aggressive cropping, 3D techniques are often undermined by fragile…
Effective scene representation is critical for the visual grounding ability of representations, yet existing methods for 3D Visual Grounding are often constrained. They either only focus on geometric and visual cues, or, like traditional 3D…
Learning to understand dynamic 3D scenes from imagery is crucial for applications ranging from robotics to scene reconstruction. Yet, unlike other problems where large-scale supervised training has enabled rapid progress, directly…
Photogrammetric 3D reconstruction has long relied on traditional Structure-from-Motion (SfM) and Multi-View Stereo (MVS) methods, which provide high accuracy but face challenges in speed and scalability. Recently, learning-based MVS methods…
Three-dimensional (3D) point cloud analysis has become one of the attractive subjects in realistic imaging and machine visions due to its simplicity, flexibility and powerful capacity of visualization. Actually, the representation of scenes…
In autonomous driving, robust place recognition is critical for global localization and loop closure detection. While inter-modality fusion of camera and LiDAR data in multimodal place recognition (MPR) has shown promise in overcoming the…
This work proposes a new method for place recognition based on the scene architecture. From depth video, we compute the 3D model and we derive and describe geometrically the 2D map from which the scene descriptor is deduced to constitute…
Existing deep methods produce highly accurate 3D reconstructions in stereo and multiview stereo settings, i.e., when cameras are both internally and externally calibrated. Nevertheless, the challenge of simultaneous recovery of camera poses…
We present CogniMap3D, a bioinspired framework for dynamic 3D scene understanding and reconstruction that emulates human cognitive processes. Our approach maintains a persistent memory bank of static scenes, enabling efficient spatial…
The current modus operandi in adapting pre-trained models involves updating all the backbone parameters, ie, full fine-tuning. This paper introduces Visual Prompt Tuning (VPT) as an efficient and effective alternative to full fine-tuning…
Vision-language models (VLM) excel at general understanding yet remain weak at dynamic spatial reasoning (DSR), i.e., reasoning about the evolvement of object geometry and relationship in 3D space over time, largely due to the scarcity of…
Pre-trained point cloud models have found extensive applications in 3D understanding tasks like object classification and part segmentation. However, the prevailing strategy of full fine-tuning in downstream tasks leads to large per-task…
Dynamic 3D point cloud sequences serve as one of the most common and practical representation modalities of dynamic real-world environments. However, their unstructured nature in both spatial and temporal domains poses significant…
Pose transfer of human videos aims to generate a high fidelity video of a target person imitating actions of a source person. A few studies have made great progress either through image translation with deep latent features or neural…