Related papers: Pose-Guided Residual Refinement for Interpretable …

Visual localization has traditionally been formulated as a pair-wise pose regression problem. Existing approaches mainly estimate relative poses between two images and employ a late-fusion strategy to obtain absolute pose estimates.…

Observational noise, inaccurate segmentation and ambiguity due to symmetry and occlusion lead to inaccurate object pose estimates. While depth- and RGB-based pose refinement approaches increase the accuracy of the resulting pose estimates,…

Current works focus on addressing the remote sensing change detection task using bi-temporal images. Although good performance can be achieved, however, seldom of they consider the motion cues which may also be vital. In this work, we…

Pre-defined 3D object templates are widely used in 3D reconstruction of hand-object interactions. However, they often require substantial manual efforts to capture or source, and inherently restrict the adaptability of models to…

The generation of realistic and contextually relevant co-speech gestures is a challenging yet increasingly important task in the creation of multimodal artificial agents. Prior methods focused on learning a direct correspondence between…

Pose refinement is an interesting and practically relevant research direction. Pose refinement can be used to (1) obtain a more accurate pose estimate from an initial prior (e.g., from retrieval), (2) as pre-processing, i.e., to provide a…

Finding local features that are repeatable across multiple views is a cornerstone of sparse 3D reconstruction. The classical image matching paradigm detects keypoints per-image once and for all, which can yield poorly-localized features and…

Most of the recent deep learning-based 3D human pose and mesh estimation methods regress the pose and shape parameters of human mesh models, such as SMPL and MANO, from an input image. The first weakness of these methods is an appearance…

Text-to-Image (T2I) models and Unified Multimodal Models (UMMs) have achieved remarkable progress in visual generation. However, their reliance on a single-pass generation paradigm limits their ability to handle complex prompts requiring…

Most previous learning-based visual odometry (VO) methods take VO as a pure tracking problem. In contrast, we present a VO framework by incorporating two additional components called Memory and Refining. The Memory component preserves…

Text-to-image person re-identification (ReID) aims to search for pedestrian images of an interested identity via textual descriptions. It is challenging due to both rich intra-modal variations and significant inter-modal gaps. Existing…

Text-to-motion generation requires not only grounding local actions in language but also seamlessly blending these individual actions to synthesize diverse and realistic global motions. However, existing motion generation methods primarily…

Recent advances in generative modeling and tokenization have driven significant progress in text-to-motion generation, leading to enhanced quality and realism in generated motions. However, effectively leveraging textual information for…

Despite remarkable progress in Multimodal Large Language Models (MLLMs), these models still struggle with fine-grained understanding tasks. In this work, we propose Procedurally Generated Tasks (PGT), a simple data-driven framework that…

Recent advances in text-to-image (T2I) generation have achieved impressive results, yet existing models often struggle with simple or underspecified prompts, leading to suboptimal image-text alignment, aesthetics, and quality. We propose a…

State-of-the-art object pose estimation methods are prone to generating geometrically infeasible pose hypotheses. This problem is prevalent in dexterous manipulation, where estimated poses often intersect with the robotic hand or are not…

We present Lang2Motion, a framework for language-guided point trajectory generation by aligning motion manifolds with joint embedding spaces. Unlike prior work focusing on human motion or video synthesis, we generate explicit trajectories…

Existing vector quantization (VQ) based autoregressive models follow a two-stage generation paradigm that first learns a codebook to encode images as discrete codes, and then completes generation based on the learned codebook. However, they…

3D human motion generation is crucial for creative industry. Recent advances rely on generative models with domain knowledge for text-driven motion generation, leading to substantial progress in capturing common motions. However, the…

We present personalized residuals and localized attention-guided sampling for efficient concept-driven generation using text-to-image diffusion models. Our method first represents concepts by freezing the weights of a pretrained…