Synthesizing a novel view from a single input image is a challenging task. Traditionally, this task was approached by estimating scene depth, warping, and inpainting, with machine learning models enabling parts of the pipeline. More recently, generative models are being increasingly employed in novel view synthesis (NVS), often encompassing the entire end-to-end system. In this work, we adapt a modern diffusion model architecture for end-to-end NVS in the pixel space, substantially outperforming previous state-of-the-art (SOTA) techniques. We explore different ways to encode geometric information into the network. Our experiments show that while these methods may enhance performance, their impact is minor compared to utilizing improved generative models. Moreover, we introduce a novel NVS training scheme that utilizes single-view datasets, capitalizing on their relative abundance compared to their multi-view counterparts. This leads to improved generalization capabilities to scenes with out-of-domain content.1

The assembly planning problem has received significant attention due to its importance in autonomous manufacturing. Typical assembly planners assume that parts have nominal shapes, while in reality their geometry varies according to the tolerance specifications. To account for toleranced parts, an assembly plan must be feasible for all possible variations of its components. Despite its practical importance, very few works address this problem. This paper presents a general framework for mechanical assembly planning with toleranced planar parts and shows how to incorporate it into existing planners. Our framework uses a general tolerancing model for parts: vertices are standard elementary functions of the part dimensions, which are allowed to vary within tolerance intervals. The relative position of parts is uniquely determined by an assembly graph, which defines constraints between features of neighboring parts. The assembly graph supports placements of parts with rotational degrees of freedom, cyclic relations, and conditional constraints, which occur in non-nominal contacts between edges. Using this framework, we show how to augment existing algorithms for useful motion types, including single and multiple step translations, and infinitesimal rigid motions. We demonstrate the dramatic reduction in the number of valid assembly plans when tolerances are introduced.