373 citations · 709 across the 54 of their papers we have counts for
61 papers
Learning Spherical Occupancy Profiles for Multi-View 3D Reconstruction and Generation
YiHsuan Tsai
We study spherical occupancy profiles-the ray-wise occupancy probability profiles P(r) = T(r) o(r) distilled from multi-view 3D Gaussian reconstructions-as a unified intermediate r…
Chat-Edit-3D++: Interactive 3D and 4D Scene Editing via Large Language Models
Shuangkang Fang, Yufeng Wang, Yi-Hsuan Tsai +4
Recent work on image content manipulation based on vision-language pre-training models has been effectively extended to text-driven 3D scene editing. However, existing schemes for…
MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh
Shuangkang Fang, I-Chao Shen, Yufeng Wang +6
We present MeshLLM, a novel framework that leverages large language models (LLMs) to understand and generate text-serialized 3D meshes. Our approach addresses key limitations in ex…
IllumiCraft: Unified Geometry and Illumination Diffusion for Controllable Video Generation
Yuanze Lin, Yi-Wen Chen, Yi-Hsuan Tsai +2
Although diffusion-based models can generate high-quality and high-resolution video sequences from textual or image inputs, they lack explicit integration of geometric cues when co…
Ranking-aware adapter for text-driven image ordering with CLIP
Wei-Hsiang Yu, Yen-Yu Lin, Ming-Hsuan Yang +1
Recent advances in vision-language models (VLMs) have made significant progress in downstream tasks that require quantitative concepts such as facial age estimation and image quali…
Chat-Edit-3D: Interactive 3D Scene Editing via Text Prompts
Shuangkang Fang, Yufeng Wang, Yi-Hsuan Tsai +4
Recent work on image content manipulation based on vision-language pre-training models has been effectively extended to text-driven 3D scene editing. However, existing schemes for…
Gaga: Group Any Gaussians via 3D-aware Memory Bank
Weijie Lyu, Xueting Li, Abhijit Kundu +2
We introduce Gaga, a framework that reconstructs and segments open-world 3D scenes by leveraging inconsistent 2D masks predicted by zero-shot class-agnostic segmentation models. Co…
Diffusion-SS3D: Diffusion Model for Semi-supervised 3D Object Detection
Cheng-Ju Ho, Chen-Hsuan Tai, Yen-Yu Lin +2
Semi-supervised object detection is crucial for 3D scene understanding, efficiently addressing the limitation of acquiring large-scale 3D bounding box annotations. Existing methods…
PTT: Point-Trajectory Transformer for Efficient Temporal 3D Object Detection
Kuan-Chih Huang, Weijie Lyu, Ming-Hsuan Yang +1
Recent temporal LiDAR-based 3D object detectors achieve promising performance based on the two-stage proposal-based approach. They generate 3D box candidates from the first-stage d…
Weakly Supervised 3D Object Detection via Multi-Level Visual Guidance
Kuan-Chih Huang, Yi-Hsuan Tsai, Ming-Hsuan Yang
Weakly supervised 3D object detection aims to learn a 3D detector with lower annotation cost, e.g., 2D labels. Unlike prior work which still relies on few accurate 3D annotations,…
Text-Driven Image Editing via Learnable Regions
Yuanze Lin, Yi-Wen Chen, Yi-Hsuan Tsai +2
Language has emerged as a natural interface for image editing. In this paper, we introduce a method for region-based image editing driven by textual prompts, without the need for u…
Editing 3D Scenes via Text Prompts without Retraining
Shuangkang Fang, Yufeng Wang, Yi Yang +4
Numerous diffusion models have recently been applied to image synthesis and editing. However, editing 3D scenes is still in its early stages. It poses various challenges, such as t…
Delving into Motion-Aware Matching for Monocular 3D Object Tracking
Kuan-Chih Huang, Ming-Hsuan Yang, Yi-Hsuan Tsai
Recent advances of monocular 3D object detection facilitate the 3D multi-object tracking task based on low-cost camera sensors. In this paper, we find that the motion cue of object…
Multimodal Prompting with Missing Modalities for Visual Recognition
Yi-Lun Lee, Yi-Hsuan Tsai, Wei-Chen Chiu +1
In this paper, we tackle two challenges in multimodal learning for visual recognition: 1) when missing-modality occurs either during training or testing in real-world situations; a…
Learning Object-level Point Augmentor for Semi-supervised 3D Object Detection
Cheng-Ju Ho, Chen-Hsuan Tai, Yi-Hsuan Tsai +2
Semi-supervised object detection is important for 3D scene understanding because obtaining large-scale 3D bounding box annotations on point clouds is time-consuming and labor-inten…
360-MLC: Multi-view Layout Consistency for Self-training and Hyper-parameter Tuning
Bolivar Solarte, Chin-Hsuan Wu, Yueh-Cheng Liu +2
We present 360-MLC, a self-training method based on multi-view layout consistency for finetuning monocular room-layout models using unlabeled 360-images only. This can be valuable…
3D-PL: Domain Adaptive Depth Estimation with 3D-aware Pseudo-Labeling
Yu-Ting Yen, Chia-Ni Lu, Wei-Chen Chiu +1
For monocular depth estimation, acquiring ground truths for real data is not easy, and thus domain adaptation methods are commonly adopted using the supervised synthetic data. Howe…
BiFuse++: Self-supervised and Efficient Bi-projection Fusion for 360 Depth Estimation
Fu-En Wang, Yu-Hsuan Yeh, Yi-Hsuan Tsai +2
Due to the rise of spherical cameras, monocular 360 depth estimation becomes an important technique for many applications (e.g., autonomous systems). Thus, state-of-the-art framewo…
MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation
Inkyu Shin, Yi-Hsuan Tsai, Bingbing Zhuang +5
Test-time adaptation approaches have recently emerged as a practical solution for handling domain shift without access to the source domain data. In this paper, we propose and expl…
On Generalizing Beyond Domains in Cross-Domain Continual Learning
Christian Simon, Masoud Faraki, Yi-Hsuan Tsai +5
Humans have the ability to accumulate knowledge of new tasks in varying conditions, but deep neural networks often suffer from catastrophic forgetting of previously learned knowled…
Learning Semantic Segmentation from Multiple Datasets with Label Shifts
Dongwan Kim, Yi-Hsuan Tsai, Yumin Suh +4
With increasing applications of semantic segmentation, numerous datasets have been proposed in the past few years. Yet labeling remains expensive, thus, it is desirable to jointly…
Self-Supervised Feature Learning from Partial Point Clouds via Pose Disentanglement
Meng-Shiun Tsai, Pei-Ze Chiang, Yi-Hsuan Tsai +1
Self-supervised learning on point clouds has gained a lot of attention recently, since it addresses the label-efficiency and domain-gap problems on point cloud tasks. In this paper…
360-DFPE: Leveraging Monocular 360-Layouts for Direct Floor Plan Estimation
Bolivar Solarte, Yueh-Cheng Liu, Chin-Hsuan Wu +2
We present 360-DFPE, a sequential floor plan estimation method that directly takes 360-images as input without relying on active sensors or 3D information. Our approach leverages a…
Semi-supervised Multi-task Learning for Semantics and Depth
Yufeng Wang, Yi-Hsuan Tsai, Wei-Chih Hung +3
Multi-Task Learning (MTL) aims to enhance the model generalization by sharing representations between related tasks for better performance. Typical MTL methods are jointly trained…