Related papers: LoST: Level of Semantics Tokenization for 3D Shape…

Annotating lots of 3D medical images for training segmentation models is time-consuming. The goal of weakly supervised semantic segmentation is to train segmentation models without using any ground truth segmentation masks. Our work…

Traditionally, algorithms that learn to segment object instances in 2D images have heavily relied on large amounts of human-annotated data. Only recently, novel approaches have emerged tackling this problem in an unsupervised fashion.…

The ability to identify whether or not a test sample belongs to one of the semantic classes in a classifier's training set is critical to practical deployment of the model. This task is termed open-set recognition (OSR) and has received…

LiDAR relocalization has attracted increasing attention as it can deliver accurate 6-DoF pose estimation in complex 3D environments. Recent learning-based regression methods offer efficient solutions by directly predicting global poses…

Reasoning segmentation aims to segment target objects in complex scenes based on human intent and spatial reasoning. While recent multimodal large language models (MLLMs) have demonstrated impressive 2D image reasoning segmentation,…

We propose an online 3D semantic segmentation method that incrementally reconstructs a 3D semantic map from a stream of RGB-D frames. Unlike offline methods, ours is directly applicable to scenarios with real-time constraints, such as…

Conventional sensor-based localization relies on high-precision maps, which are generally built using specialized mapping techniques involving high labor and computational costs. In the architectural, engineering and construction industry,…

Time-of-Flight (ToF) cameras are subject to high levels of noise and distortions due to Multi-Path-Interference (MPI). While recent research showed that 2D neural networks are able to outperform previous traditional State-of-the-Art (SOTA)…

Token merging has emerged as an effective strategy to accelerate Vision Transformers (ViT) by reducing computational costs. However, existing methods primarily rely on the visual token's feature similarity for token merging, overlooking the…

Layer-wise quantization is a key technique for efficiently compressing large models without expensive retraining. Previous methods typically quantize the weights of each layer by "uniformly" optimizing the layer reconstruction loss across…

We study the problem of unsupervised 3D semantic segmentation on raw point clouds without needing human labels in training. Existing methods usually formulate this problem into learning per-point local features followed by a simple grouping…

Long-tailed object detection (LTOD) aims to handle the extreme data imbalance in real-world datasets, where many tail classes have scarce instances. One popular strategy is to explore extra data with image-level labels, yet it produces…

3D object part segmentation is essential in computer vision applications. While substantial progress has been made in 2D object part segmentation, the 3D counterpart has received less attention, in part due to the scarcity of annotated 3D…

Quantization is an indispensable technique for serving Large Language Models (LLMs) and has recently found its way into LoRA fine-tuning. In this work we focus on the scenario where quantization and LoRA fine-tuning are applied together on…

Large Language Models (LLMs) demonstrate significant advantages in leveraging structured world knowledge and multi-step reasoning capabilities. However, fundamental challenges arise when transforming LLMs into real-world recommender systems…

Token representations in high-dimensional latent spaces often exhibit redundancy, limiting computational efficiency and reducing structural coherence across model layers. Hierarchical latent space folding introduces a structured…

Automatically highlighting words that cause semantic differences between two documents could be useful for a wide range of applications. We formulate recognizing semantic differences (RSD) as a token-level regression task and study three…

Semantic segmentation has recently achieved notable advances by exploiting "class-level" contextual information during learning. However, these approaches simply concatenate class-level information to pixel features to boost the pixel…

The visual understanding are often approached from 3 granular levels: image, patch and pixel. Visual Tokenization, trained by self-supervised reconstructive learning, compresses visual data by codebook in patch-level with marginal…

Recently, multi-view diffusion-based 3D generation methods have gained significant attention. However, these methods often suffer from shape and texture misalignment across generated multi-view images, leading to low-quality 3D generation…