3 papers
cs.CV2025
Local Prompt Adaptation for Style-Consistent Multi-Object Generation in Diffusion Models
Ankit Sanjyal
Diffusion models have become a powerful backbone for text-to-image generation, producing high-quality visuals from natural language prompts. However, when prompts involve multiple…
cs.GR2025
RectifiedHR: High-Resolution Diffusion via Energy Profiling and Adaptive Guidance Scheduling
Ankit Sanjyal
High-resolution image synthesis with diffusion models often suffers from energy instabilities and guidance artifacts that degrade visual quality. We analyze the latent energy lands…
cs.CV2025
Limitations of NERF with pre-trained Vision Features for Few-Shot 3D Reconstruction
Ankit Sanjyal
Neural Radiance Fields (NeRF) have revolutionized 3D scene reconstruction from sparse image collections. Recent work has explored integrating pre-trained vision features, particula…