A batch size of 2048 is used during training with a learning rate of 1e-4. Both training and rendering were conducted using A WS. A.2 PixelNeRF We used a constant learning rate of 1e-4. To train PixelNeRF on Objaverse-XL we render the meshes in Blender. Each model is normalize to a bounding cube. We believe that models such as Zero123-XL, and those trained on Objaverse-XL, will enhance the ease of 3D content creation, enabling broader accessibility for individuals and businesses to participate.

There are two operations in our data augmentation pipeline that changes the scale or layout of the image, i.e ., random resized crop and random horizontal flip. This is followed by a resize operation to recover the intersect part to the original size ( e.g ., RoIAlign to recover the original spatial layout. The total stride is 16 (FCN-16s [20]). Intuitively, each prototype can be viewed as the cluster center of a semantic class. During inference, we only take the teacher model parameterized by ξ .

Large language models have recently shown a remarkable ability for few-shot learning, including patterns of algorithmic nature. However, it is still an open question to determine what kind of patterns these models can capture and how manyexamples theyneedintheirprompts.

We include screenshots of the reviewing tools we built to analyze model mistakes. Figure 3: A screenshot of the UI we built to review model predictions. We also flagged images as problematic if the ground truth label for the image was incorrect. 'siberian husky' label would be considered correct, whereas a prediction of'siberian husky' for an All siberian huskies and malamutes are also eskimo dogs. Sunglass and sunglasses are the same class (bidirectional).