In this section, we describe in detail the proposed architecture and its implementation. Our architecture is composed by an encoder and a decoder. The encoder receives as input a predefined number of learnable latent probes LP, together with the point coordinates of the target point cloud XT. Each layer of the encoder performs an operation of cross-attention between LP and XT followed by a self-attention on LP. Each attention is followed by a feed-forward layer.

To leverage the complementary merits of both worlds, we propose BetterDepth to achieve geometrically correct affine-invariant MDE while capturing fine details.

We now investigate the relation between the attention entropy and the token number. The revised code are shown in Algorithm 1. Both of them are top-ranked parameter files for downloading. Experiments are conducted on a server with Intel(R) Xeon(R) Gold 6226R CPUs @ 2.90GHz and We conduct an text-based pairwise preference test. The screenshot is depicted in Figure 1.

Reversing the process is not immediately obvious and thus several schedulers were proposed [23, 26, 31, 58]. In this paper, we employ DDIM [58] scheduler, a popular deterministic scheduler. Other deterministic scheduler would be suitable, and we show in section I below that our method performs well with other schedulers.