Search papers, labs, and topics across Lattice.
This paper introduces DAC-Pose, a dual-agent collaborative framework designed to enhance pose-guided human generation by addressing severe visual artifacts that arise during significant viewpoint shifts. By integrating the Prior Semantic Reasoning (PSR) agent for cognitive reasoning and the Discrepancy-Aware Visual Encoding (DAVE) agent for spatial perception, DAC-Pose creates an autonomous feedback loop that ensures high-fidelity detail synthesis. Experimental results on the DeepFashion and Market-1501 benchmarks demonstrate that DAC-Pose significantly improves texture alignment and identity consistency compared to traditional methods.
DAC-Pose achieves remarkable fidelity in human generation, maintaining texture and identity consistency even under extreme viewpoint changes.
AI agents have emerged as a powerful new paradigm in generative image synthesis, enabling systems to perform complex semantic reasoning rather than passive pixel-level mapping. In pose-guided human generation, conventional methods inevitably produce severe visual artifacts under drastic viewpoint shifts, fundamentally because they lack the cognitive capacity to logically deduce unseen regions and model complex spatial deformations. To bridge this gap, we propose DAC-Pose, a novel agent-driven multimodal framework that reformulates single-view human generation as a collaborative dual-agent system. DAC-Pose integrates two complementary components, namely, the Prior Semantic Reasoning (PSR) agent and the Discrepancy-Aware Visual Encoding (DAVE) agent. Functioning as a cognitive engine, PSR utilizes collaborative reasoning to deduce the fine-grained attributes of unseen regions. Concurrently, acting as a specialized visual perception agent, DAVE quantifies and encodes viewpoint-induced spatial misalignments, continuously feeding robust spatial constraints back into the generative process. This autonomous feedback loop between semantic deduction and visual perception ensures high-fidelity detail synthesis. Extensive experiments on the DeepFashion and Market-1501 benchmarks validate the superiority of our agent-driven paradigm. Notably, DAC-Pose excels in preserving texture alignment and identity consistency under drastic viewpoint changes. The code is available at https://github.com/AIVRC/DAC-Pose.
