2 citations · 2 across the 13 of their papers we have counts for
13 papers
AquaFlow: A Monocular Gaussian Splatting SLAM for Underwater Streaming Reconstruction
Yingxiang Xu, Kerui Ren, Wenqi Guo +4
Recent monocular 3D Gaussian Splatting (3DGS) streaming reconstruction methods have achieved impressive performance by balancing reconstruction quality and efficiency. However, ext…
MissingBench-Verified: Probing Vision-Language Models' Inability to Detect Missing Object Parts
Wenqi Marshall Guo, Qingyun Qian, Shiyu Zhou +2
Vision Language Models (VLMs) are well known for hallucinating non-existent objects in images. Objects with missing parts present a unique challenge for VLMs, stemming from both re…
Gen2-IC: Bridging Generative Models and Image Codecs through Latent Transport
Yinhuan Huang, Hao Cao, Pu chen +3
Diffusion-based image compression has achieved strong perceptual quality at ultra-low bitrates. However, existing codecs are often tied to specific backbones and specialized compon…
ContextCodec: Content-Focused Context Guidance for Ultra-Low Bitrate Speech Coding
Chengbin Liang, Wenqi Guo, Hao Cao +1
Neural speech codecs enable low-bitrate speech communication, yet at ultra-low bitrates (< 1000 bps) preserving perceptual quality and intelligibility is challenging. Existing desi…
Efficient Learned Image Compression without Entropy Coding
Hao Cao, Wenqi Guo, Zhijin Qin +1
Entropy coding is widely used in typical learned image compression (LIC) that converts latents into a compact bitstream. However, entropy coding is typically sequential and becomes…
Generalizable 3D Gaussian Splatting enabled Semantic Coding for Real-Time Immersive Video Communications
Dingxi Yang, Wenqi Guo, Yue Liu +2
Real-time immersive video communications, particularly high-fidelity 3D telepresence, necessitates a synergistic balance between instantaneous dynamic scene reconstruction and high…
ProGIC: Progressive and Lightweight Generative Image Compression with Residual Vector Quantization
Hao Cao, Chengbin Liang, Wenqi Guo +2
Recent advances in generative image compression (GIC) have delivered remarkable improvements in perceptual quality. However, many GICs rely on large-scale and rigid models, which s…
FaceLinkGen: A Re-evaluation of Identity Leakage in Privacy-Preserving Face Recognition and Face Anonymization Systems Using Simple Distillation
Wenqi Guo, Mohamed Shehata, Qingyun Qian +1
Privacy-preserving face recognition (PPFR) and face anonymization have different goals, but both must retain some identity-related information for their intended use. We show that…
Position: Universal Aesthetic Alignment Narrows Artistic Expression
Wenqi Marshall Guo, Qingyun Qian, Khalad Hasan +1
Over-aligning image generation models to a generalized aesthetic preference conflicts with user intent, particularly when "anti-aesthetic" outputs are requested for artistic or cri…
Position: The Pitfalls of Over-Alignment: Overly Caution Health-Related Responses From LLMs are Unethical and Dangerous
Wenqi Marshall Guo, Yiyang Du, Heidi J. S. Tworek +1
Large Language Models (LLMs) are usually aligned with "human values/preferences" to prevent harmful output. Discussions around the alignment of Large Language Models (LLMs) general…
VSF: Simple, Efficient, and Effective Negative Guidance in Few-Step Image Generation Models By Value Sign Flip
Wenqi Guo, Shan Du
We introduce Value Sign Flip (VSF), a simple and efficient method for incorporating negative prompt guidance in few-step diffusion and flow-matching image generation models. Unlike…
ZS-VCOS: Zero-Shot Video Camouflaged Object Segmentation By Optical Flow and Open Vocabulary Object Detection
Wenqi Guo, Mohamed Shehata, Shan Du
Camouflaged object segmentation presents unique challenges compared to traditional segmentation tasks, primarily due to the high similarity in patterns and colors between camouflag…
LangGas: Introducing Language in Selective Zero-Shot Background Subtraction for Semi-Transparent Gas Leak Detection with a New Dataset
Wenqi Guo, Yiyang Du, Shan Du
Gas leakage poses a significant hazard that requires prevention. Traditionally, human inspection has been used for detection, a slow and labour-intensive process. Recent research h…