7 papers
Towards Alias-Free 4D Gaussian Representations with Motion-Aware Filtering
Ankit Dhiman, Kunal A Kathare, Pranav Vignesh +2
Novel-view synthesis of dynamic scenes, crucial for AR/VR applications, remains a challenging problem. Recent methods adapt representations like 3D Gaussian Splatting (3DGS) and Ne…
UniC-Lift: Unified 3D Instance Segmentation via Contrastive Learning
Ankit Dhiman, Srinath R, Jaswanth Reddy +2
3D Gaussian Splatting (3DGS) and Neural Radiance Fields (NeRF) have advanced novel-view synthesis. Recent methods extend multi-view 2D segmentation to 3D, enabling instance/semanti…
Objects in Generated Videos Are Slower Than They Appear: Models Suffer Sub-Earth Gravity and Don't Know Galileo's Principle...for now
Varun Varma Thozhiyoor, Shivam Tripathi, Venkatesh Babu Radhakrishnan +1
Video generators are increasingly evaluated as potential world models, which requires them to encode and understand physical laws. We investigate their representation of a fundamen…
Harnessing Diffusion-Generated Synthetic Images for Fair Image Classification
Abhipsa Basu, Aviral Gupta, Abhijnya Bhat +1
Image classification systems often inherit biases from uneven group representation in training data. For example, in face datasets for hair color classification, blond hair may be…
Kontinuous Kontext: Continuous Strength Control for Instruction-based Image Editing
Rishubh Parihar, Or Patashnik, Daniil Ostashev +3
Instruction-based image editing offers a powerful and intuitive way to manipulate images through natural language. Yet, relying solely on text instructions limits fine-grained cont…
A Granular Study of Safety Pretraining under Model Abliteration
Shashank Agnihotri, Jonas Jakubassa, Priyam Dey +4
Open-weight LLMs can be modified at inference time with simple activation edits, which raises a practical question for safety: do common safety interventions like refusal training…