61 to 70 of 70 Results
Sep 25, 2024
Xu, Qianxiong; Lin, Guosheng; Loy, Chen Change; Long, Cheng; Li, Ziyue; Zhao, Rui, 2024, "Eliminating Feature Ambiguity for Few-Shot Segmentation", https://doi.org/10.21979/N9/CIOE8Y, DR-NTU (Data), V1
Recent advancements in few-shot segmentation (FSS) have exploited pixel-by-pixel matching between query and support features, typically based on cross attention, which selectively activate query foreground (FG) features that correspond to the same-class support FG features. Howev... |
Sep 25, 2024
Feng, Ruicheng; Li, Chongyi; Loy, Chen Change, 2024, "Kalman-Inspired Feature Propagation for Video Face Super-Resolution", https://doi.org/10.21979/N9/FMVNYY, DR-NTU (Data), V1
Despite the promising progress of face image super-resolution, video face super-resolution remains relatively under-explored. Existing approaches either adapt general video super-resolution networks to face datasets or apply established face image super-resolution models independ... |
Sep 20, 2024
Hu, Tao; Hong, Fangzhou; Liu, Ziwei, 2024, "StructLDM: Structured Latent Diffusion for 3D Human Generation", https://doi.org/10.21979/N9/BXUEXV, DR-NTU (Data), V1
Recent 3D human generative models have achieved remarkable progress by learning 3D-aware GANs from 2D images. However, existing 3D human generative methods model humans in a compact 1D latent space, ignoring the articulated structure and semantics of human body topology. In this... |
Loy, Chen Change, 2024, "EdgeSAM", https://doi.org/10.21979/N9/KF8798, DR-NTU (Data), V2
We present EdgeSAM, an accelerated variant of the Segment Anything Model (SAM), optimized for efficient execution on edge devices with minimal compromise in performance. Our approach involves distilling the original ViT-based SAM image encoder into a purely CNN-based architecture... |
Loy, Chen Change, 2024, "CodeFormer", https://doi.org/10.21979/N9/X3IBKH, DR-NTU (Data), V4
Blind face restoration is a highly ill-posed problem that often requires auxiliary guidance to 1) improve the mapping from degraded inputs to desired outputs, or 2) complement high-quality details lost in the inputs. In this paper, we demonstrate that the learned discrete codeboo... |
Loy, Chen Change, 2024, "MMDetection3D", https://doi.org/10.21979/N9/15XUKI, DR-NTU (Data), V1
MMDetection3D is an open source object detection toolbox based on PyTorch, towards the next-generation platform for general 3D detection. It is a part of the OpenMMLab project. |
Appointment: Professor Research topics: • Dr Loy's research interests include computer vision and deep learning with a focus on image/video restoration and enhancement, creative content generation, and representation learning. For more information, visit this webpage. |
Jun 20, 2024
Wu, Haoning; Zhang, Erli; Liao, Liang; Chen, Chaofeng; Hou, Jingwen; Wang, Annan; Sun, Wenxiu; Yan, Qiong; Lin, Weisi, 2024, "Replication Data for: Towards Explainable In-the-Wild Video Quality Assessment: A Database and a Language-Prompted Approach", https://doi.org/10.21979/N9/ELWDPE, DR-NTU (Data), V1
A large-scale in-the-wild VQA database, named Maxwell, created to gather more than two million human opinions across 13 specific quality-related factors, including technical distortions e.g. noise, flicker and aesthetic factors e.g. contents. |
Jun 20, 2024
Wu, Haoning; Zhang, Zicheng; Zhang, Erli; Chen, Chaofeng; Liao, Liang; Wang, Annan; Li, Chunyi; Sun, Wenxiu; Yan, Qiong; Zhai, Guangtao; Lin, Weisi, 2024, "Replication Data for: Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision", https://doi.org/10.21979/N9/M41ERD, DR-NTU (Data), V1
We present Q-Bench, a holistic benchmark crafted to systematically evaluate potential abilities of MLLMs on three realms: low-level visual perception, low-level visual description, and overall visual quality assessment. |
Jun 20, 2024
Wu, Haoning; Zhang, Zicheng; Zhang, Erli; Chen, Chaofeng; Liao, Liang; Wang, Annan; Xu, Kaixin; Li, Chunyi; Hou, Jingwen; Zhai, Guangtao; Xue, Geng; Sun, Wenxiu; Yan, Qiong; Lin, Weisi, 2024, "Replication Data for: Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models", https://doi.org/10.21979/N9/GPLPNI, DR-NTU (Data), V1
The dataset consisting of human natural language feedback on low-level vision. |
