Related papers: HPSv3: Towards Wide-Spectrum Human Preference Scor…
Large Visual Language Models (LVLMs) increasingly rely on preference alignment to ensure reliability, which steers the model behavior via preference fine-tuning on preference data structured as ``image - winner text - loser text'' triplets.…
Capturing the diversity of people in images is challenging: recent literature tends to focus on diversifying one or two attributes, requiring expensive attribute labels or building classifiers. We introduce a diverse people image ranking…
To prevent misinformation and social issues arising from trustworthy-looking content generated by LLMs, it is crucial to develop efficient and reliable methods for identifying the source of texts. Previous approaches have demonstrated…
Recent advances in zero-shot text-to-3D human generation, which employ the human model prior (eg, SMPL) or Score Distillation Sampling (SDS) with pre-trained text-to-image diffusion models, have been groundbreaking. However, SDS may provide…
Direct Preference Optimization (DPO) has emerged as a powerful approach to align text-to-image (T2I) models with human feedback. Unfortunately, successful application of DPO to T2I models requires a huge amount of resources to collect and…
Recent advances in Score Distillation Sampling (SDS) have improved 3D human generation from textual descriptions. However, existing methods still face challenges in accurately aligning 3D models with long and complex textual inputs. To…
Can Visual Language Models (VLMs) effectively capture human visual preferences? This work addresses this question by training VLMs to think about preferences at test time, employing reinforcement learning methods inspired by DeepSeek R1 and…
Generating high-quality, photorealistic textures for 3D human avatars remains a fundamental yet challenging task in computer vision and multimedia field. However, real paired front and back images of human subjects are rarely available with…
Graphic layouts serve as an important and engaging medium for visual communication across different channels. While recent layout generation models have demonstrated impressive capabilities, they frequently fail to align with nuanced human…
Human body restoration, as a specific application of image restoration, is widely applied in practice and plays a vital role across diverse fields. However, thorough research remains difficult, particularly due to the lack of benchmark…
This study introduces HQ-Edit, a high-quality instruction-based image editing dataset with around 200,000 edits. Unlike prior approaches relying on attribute guidance or human feedback on building datasets, we devise a scalable data…
Text-to-3D generation automates 3D content creation from textual descriptions, which offers transformative potential across various fields. However, existing methods often struggle to align generated content with human preferences, limiting…
The increasing availability of image-text pairs has largely fueled the rapid advancement in vision-language foundation models. However, the vast scale of these datasets inevitably introduces significant variability in data quality, which…
Users often possess a clear visual intent but struggle to articulate it precisely in language. This intention-expression gap makes aligning generated images with latent visual preferences a fundamental challenge in text-to-image diffusion…
Human pose estimation on medium and small scales has long been a significant challenge in this field. Most existing methods focus on restoring high-resolution feature maps by stacking multiple costly deconvolutional layers or by…
The goal of aligning language models to human preferences requires data that reveal these preferences. Ideally, time and money can be spent carefully collecting and tailoring bespoke preference data to each downstream application. However,…
Recent studies have demonstrated the exceptional potentials of leveraging human preference datasets to refine text-to-image generative models, enhancing the alignment between generated images and textual prompts. Despite these advances,…
Human pose and shape (HPS) estimation with lensless imaging is not only beneficial to privacy protection but also can be used in covert surveillance scenarios due to the small size and simple structure of this device. However, this task…
Large vision-language models (LVLMs) often fail to align with human preferences, leading to issues like generating misleading content without proper visual context (also known as hallucination). A promising solution to this problem is using…
RLHF techniques like DPO can significantly improve the generation quality of text-to-image diffusion models. However, these methods optimize for a single reward that aligns model generation with population-level preferences, neglecting the…